Developer-tools MCP server

OpenTakeoff

Version history of discovered tools, schemas, and declared agent authority.

View watchlist

DistributionDistribution: npm
Packageopentakeoff-mcp
Latest analyzed version0.9.105
Current tool count62
Latest analysisNov 16, 2026
Package source

OBSERVED INTERFACE

Capability surface

Modelara’s observed declarations are shown separately from its derived effect classifications.

3 releases analyzed0.9.99 → 0.9.105Latest: 0.9.105
  • read5
  • write12
  • destructive3
  • unknown42

Unknown means Valyd could not determine the capability's effect confidently from the declared interface and static evidence. It is not treated as safe.

Package
opentakeoff-mcp@0.9.105
Registry
npm
Published
Nov 7, 2026
Integrity
sha512-dKkvVARQ7tlrt11ehFzD/VqRakxA/ogDV3rRXrxYlfUJ5509UZA7eGnmU408KEdGZfnfXwCbxLheTpKvIMIqtg==
Analyzer
modelara v0.1.8 · policy not recorded
Repository
https://github.com/Kentucky-ai/opentakeoff

62 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
annotatekentucky-ai-opentakeoff:tool:annotate
Observed interface and hashes

Place an annotation on a sheet — a note ABOUT the work, never a measurement of it. Types: cloud and highlight take rect:[[x0,y0],[x1,y1]] (a revision cloud around an area, a highlight box over it), text takes at:[x,y], callout takes at:[x,y] plus target:[x,y] (the point its leader aims at), arrow takes from:[x,y] and to:[x,y] (tail and head — plank/seam direction, the markup flooring drawings use most; #150), bubble takes at:[x,y] plus optional r (a keynote/detail circle carrying centered text), dimension takes from:[x,y] and to:[x,y] (its two measured endpoints) and labels itself with the length between them at the sheet's scale — drawn as a dimension line with end ticks and the measurement centered. A dimension states a REAL length, so it is the one annotation the scale gate applies to: on an unscaled sheet it refuses exactly like the measure tools (set_scale first) rather than dressing a px figure up as feet. It still touches no quantity — a dimension is a note about a distance, not a takeoff line item. Pass condition to attach the note to a finish tag, which is what makes it part of that SCOPE rather than a floating remark: it then wears the condition's colour on the canvas and in the marked-set PDF, and travels with it into the report. The tag is minted on first touch like measure_polygon, so you can annotate CPT-1 before anything is traced for it. Omit condition for a note about the sheet itself. Write {{qty}} in the text to quote the linked condition's live measured quantity (multiplier applied, no waste): "x{{qty}} fixtures" reads "x6 EA fixtures" on the sheet and follows every later count; the stored text keeps the field, and list_annotations reports text_resolved. No review gate: the pencil-not-ink rule exists to stop an agent inventing geometry, and a cloud reading "verify substrate" is not geometry. It touches no quantity. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "at": {
      "additionalItems": false,
      "description": "Anchor point (image px) — text, callout, and bubble (the circle's center)",
      "items": [
        {
          "type": "number"
        },
        {
          "type": "number"
        }
      ],
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "condition": {
      "description": "Finish tag to attach this note to, e.g. 'CPT-1' (minted on first use). Omit for an unattached sheet note",
      "type": "string"
    },
    "from": {
      "additionalItems": false,
      "description": "Arrow tail / dimension start (image px)",
      "items": [
        {
          "type": "number"
        },
        {
          "type": "number"
        }
      ],
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "r": {
      "description": "Bubble radius (image px); omitted → the canvas default (2% of sheet width)",
      "exclusiveMinimum": 0,
      "type": "number"
    },
    "rect": {
      "additionalItems": false,
      "description": "Corners (image px) — cloud and highlight",
      "items": [
        {
          "additionalItems": false,
          "items": [
            {
              "type": "number"
            },
            {
              "type": "number"
            }
          ],
          "maxItems": 2,
          "minItems": 2,
          "type": "array"
        },
        {
          "additionalItems": false,
          "items": [
            {
              "type": "number"
            },
            {
              "type": "number"
            }
          ],
          "maxItems": 2,
          "minItems": 2,
          "type": "array"
        }
      ],
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "sheet": {
      "description": "Sheet name or number, as sheet_info reports it",
      "type": "string"
    },
    "target": {
      "additionalItems": false,
      "description": "What a callout's leader line points at (image px)",
      "items": [
        {
          "type": "number"
        },
        {
          "type": "number"
        }
      ],
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "text": {
      "default": "",
      "description": "The note. A cloud with no text still reads as 'look here'; a bubble's text draws centered in the circle; a dimension appends it after the measured length",
      "type": "string"
    },
    "to": {
      "additionalItems": false,
      "description": "Arrow head / dimension end (image px)",
      "items": [
        {
          "type": "number"
        },
        {
          "type": "number"
        }
      ],
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "type": {
      "description": "cloud/highlight need rect; text/callout/bubble need at; callout also needs target; arrow and dimension need from + to",
      "enum": [
        "cloud",
        "text",
        "callout",
        "highlight",
        "arrow",
        "bubble",
        "dimension"
      ],
      "type": "string"
    }
  },
  "required": [
    "sheet",
    "type"
  ],
  "type": "object"
}
sha256:b746dd2890e73ddac685d0ce3469ebc0a3d45fe62ac7ab4bcada1d9ddae19ad2

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "condition": {
      "type": "string"
    },
    "condition_id": {
      "type": "string"
    },
    "id": {
      "type": "string"
    },
    "length_lf": {
      "description": "Dimension only: the measured length (real feet) the annotation will label itself with",
      "type": "number"
    },
    "note": {
      "type": "string"
    },
    "sheet": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "type": {
      "type": "string"
    }
  },
  "required": [
    "id",
    "sheet",
    "type",
    "text",
    "condition",
    "condition_id",
    "note"
  ],
  "type": "object"
}
sha256:45de11d7b260e25dcc439b02d690cc3a461de08b7d5021ec5edeeacbac012a23

Description hash: sha256:4dd5176aadf6662c4a73e75f48f9dee40cac9ad7aa83fc47c95d648df35dc99f

Interface hash: sha256:ed7bd4cd16621a02d4d39c784e5d1b41f8f95275a42b7438b36b0fb061c05b97

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/annotate",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "annotate"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:71e76f826ab9be71f54f5f40bd62a744efcf238086f8fda0ef2c92df8e8460ce"
}
toolunknown0.9.990.9.100
apply_ruleskentucky-ai-opentakeoff:tool:apply_rules
Observed interface and hashes

Re-run the correction rules the takeoff arrived with (#207) — the lessons an estimator TAUGHT the canvas (#88): "every room like this loses the mechanical chase." A rule is a deterministic predicate (enclosed linework islands under a size cap, inside the rule's condition's rooms), never a re-prompt. Evaluation is the same pure rules.ts engine the canvas Preview runs; the commit is the one batch the canvas's Apply makes — ONE journal entry, undo_last takes the whole batch back. Everything lands reviewed: false (this server has no review gate), and the reply's per-rule disclosure — what each rule produced, what was skipped, with ids — IS your preview: read it, then view_sheet overlay:true. Idempotent by construction: any candidate an existing deduct already covers is dropped by the engine, so re-running after new rooms commit is the intended workflow and never double-deducts. Rules arrive ONLY via import_takeoff (minting a new rule is an estimator's correction and stays behind the canvas's human Preview→Apply gate); with none imported this refuses. Pass sheet to scan one sheet; omit it to scan every sheet holding the rules' rooms. Uncalibrated and scanned-raster sheets come back in skipped_sheets, named.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "sheet": {
      "description": "Scan only this sheet (default: every sheet holding the rules' conditions' rooms)",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:f4f93e80f5d142a1d9807eac9c471127af270c46b7b72f61208fef2c71500e3f

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "committed": {
      "description": "Deducts committed across all rules — 0 is a result (idempotence)",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "note": {
      "type": "string"
    },
    "rules": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "condition": {
            "description": "The finish tag whose rooms were scanned",
            "type": "string"
          },
          "deduct_sf": {
            "type": "number"
          },
          "label": {
            "description": "The rule's own plain-language statement, minted at creation",
            "type": "string"
          },
          "produced": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "rule_id": {
            "type": "string"
          },
          "shape_ids": {
            "description": "The committed deducts — reviewed: false, one batch",
            "items": {
              "type": "string"
            },
            "type": "array"
          }
        },
        "required": [
          "rule_id",
          "label",
          "condition",
          "produced",
          "shape_ids",
          "deduct_sf"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "skipped_rules": {
      "description": "Rules not evaluated, named — never silently dropped",
      "items": {
        "additionalProperties": false,
        "properties": {
          "label": {
            "type": "string"
          },
          "reason": {
            "enum": [
              "inactive",
              "condition_not_in_session"
            ],
            "type": "string"
          },
          "rule_id": {
            "type": "string"
          }
        },
        "required": [
          "rule_id",
          "label",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "skipped_sheets": {
      "description": "Sheets that could not be scanned (uncalibrated, or scanned raster with no linework mask)",
      "items": {
        "additionalProperties": false,
        "properties": {
          "reason": {
            "enum": [
              "no_scale",
              "no_vector_mask"
            ],
            "type": "string"
          },
          "sheet_id": {
            "type": "string"
          }
        },
        "required": [
          "sheet_id",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "total_deduct_sf": {
      "type": "number"
    }
  },
  "required": [
    "rules",
    "committed",
    "total_deduct_sf",
    "skipped_rules",
    "skipped_sheets",
    "note"
  ],
  "type": "object"
}
sha256:a84da6a784d42a539814b59aeca4c5ccabdee91ccaa28dab7b7c1cb0d59e2524

Description hash: sha256:84eb6ec9fb2e64ca65f53a567435071a8cc3c6d022b5f41e9668b089d46a05a4

Interface hash: sha256:e1ad1dd5a4fec533f9521c143ca93dfb0cdd9e762ca0c9b248ba291f5fd04f29

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/apply_rules",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "apply_rules"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:a256b61efd9ba8b48370586b7fadc96d9623a4e8697af5adf0f60ac6d7bea2e5"
}
toolunknown0.9.990.9.100
assistant_listenkentucky-ai-opentakeoff:tool:assistant_listen
Observed interface and hashes

Wait for the person's next message in the OpenTakeoff Assistant window (after assistant_open). Returns status "message" with their text — do what they ask (with the other tools), reply with assistant_say, then call assistant_listen again. Status "timeout" = nothing typed yet: call assistant_listen again right away, saying nothing to the person. Status "sleep" = 10 quiet minutes: stop listening and tell the person in one line to say "listen" when they want you back (then call assistant_open, which reconnects without a new code).

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "wait_s": {
      "description": "Seconds to wait (default 45, max 240). Keep it under your client's tool timeout.",
      "maximum": 240,
      "minimum": 1,
      "type": "integer"
    }
  },
  "type": "object"
}
sha256:b2df353da4886d0aac45aa30133797542ab9845fb5fb3d0942876ed1cbe62239

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "idle_s": {
      "description": "Seconds since the person last wrote",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "message": {
      "description": "What the person typed (several messages joined), or null",
      "type": [
        "string",
        "null"
      ]
    },
    "status": {
      "description": "message = the person wrote; timeout = call again; sleep = stop, they are away",
      "enum": [
        "message",
        "timeout",
        "sleep"
      ],
      "type": "string"
    }
  },
  "required": [
    "status",
    "message",
    "idle_s"
  ],
  "type": "object"
}
sha256:f59833a28a3957a017e9e3a10cbc1b9e67bc66ebf0b98c476c49bfb09e42e428

Description hash: sha256:d8210137696cbeee412a2d965321f2d6794be541fcebde732a57be03bf849ba8

Interface hash: sha256:d8c4a4f52fd528e5990b033efe6b6a2418af1bfaaed8c359e95738a99dfa7e2b

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/assistant_listen",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "assistant_listen"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:c549bfef4da072e62c3d790a02ecec09a29e7c88a192c2de3e42de5626112bde"
}
toolunknown0.9.1050.9.105
assistant_openkentucky-ai-opentakeoff:tool:assistant_open
Observed interface and hashes

Open the OpenTakeoff Assistant window: the person can then talk to YOU from inside the OpenTakeoff canvas (opentakeoff.kentucky-ai.com) instead of only here. Starts a private link on 127.0.0.1 and returns a one-time pairing `code` and a `link`. Give the person the link (or the 6-letter code to type into the canvas's Assistant window), then call assistant_listen and keep calling it: each message they type arrives as its result; do the work with the other tools, answer with assistant_say, then listen again. Call it when the person asks for the OpenTakeoff assistant/window, or says "listen" after a pause.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {},
  "type": "object"
}
sha256:73fc3af6ba54a1293c44f954cf944c40d069a764ef7974e6fc74addd4231b225

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "already_paired": {
      "type": "boolean"
    },
    "code": {
      "description": "One-time pairing code the person types into the canvas's Assistant window (empty when already paired)",
      "type": "string"
    },
    "link": {
      "description": "Opens the canvas and pairs automatically — give this to the person",
      "type": "string"
    },
    "next": {
      "description": "What to tell the person, then what to call",
      "type": "string"
    },
    "port": {
      "description": "127.0.0.1 port the window connects to",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "powered_by": {
      "additionalProperties": false,
      "properties": {
        "name": {
          "description": "The AI app driving this server, as it announced itself (e.g. claude-ai, claude-code, codex-mcp-client)",
          "type": "string"
        },
        "version": {
          "type": "string"
        }
      },
      "required": [
        "name",
        "version"
      ],
      "type": "object"
    }
  },
  "required": [
    "port",
    "code",
    "link",
    "powered_by",
    "already_paired",
    "next"
  ],
  "type": "object"
}
sha256:4806a06ad7f98a6bc97dd50a321d7ccce43a817c3c868dbe20faecc1498b6309

Description hash: sha256:d88db39ffdc4a42567de5e5436d1f3df6e85636a7d83bdfb38efb6466cf9c96b

Interface hash: sha256:ff9e098b23c3bc77b52e23daec01b89f30d5ac923eb4d45179418d6ddc0d61de

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/assistant_open",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "assistant_open"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:1ac1d056eda4f3648ac5458c75b4f7cdea4b00b9b6a88ca1188997349d7066e4"
}
toolunknown0.9.1050.9.105
assistant_saykentucky-ai-opentakeoff:tool:assistant_say
Observed interface and hashes

Show your reply in the OpenTakeoff Assistant window (Markdown). Use it for every answer to a message that came through assistant_listen — the person is reading the window, not this chat. Then call assistant_listen again.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "text": {
      "description": "Your reply, Markdown",
      "minLength": 1,
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "type": "object"
}
sha256:f269e46cafa8a135d1b623d63cf35a0784df543fe5a803b6171f60b6ebe338bc

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "delivered_to": {
      "description": "Open windows that received the reply (0 = the person closed the window; it shows when they reopen)",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "delivered_to"
  ],
  "type": "object"
}
sha256:e803272e6a96f92d8e3fc7af049eec3f0ee7eed5e660447e700412e6d080ef82

Description hash: sha256:aef499f2e456b8e894eb2852a998b9c669587ccac931bb9b9dfcc7e6080fe361

Interface hash: sha256:2e2e834da448b112e1c62226cf4ed922ae2b0e4f9b659d560c832b2821ed879a

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/assistant_say",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "assistant_say"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:06d18e80c056e088757259fa22b4fcff484701ae93d417c9ca299f0b388d221c"
}
toolread0.9.1050.9.105
count_markskentucky-ai-opentakeoff:tool:count_marks
Observed interface and hashes

The COUNT TAKEOFF in one deterministic call — no seeds, no model, seconds: census every VALUE-ANNOTATED mark tag on the plan-role sheets, counted per schedule mark, committed as EA markers when asked. The identity rule is the annotated-device drafting pattern: a device is drawn as its mark tag with a value under it ("S1" over "200" — CFM on air devices, GPM on fixtures, a rating on equipment), so a tag WITH a paired value counts, a tag inside a schedule table's own region is a row label (excluded, tallied), and every other occurrence is WITHHELD with a reason and coordinates — a tag amid linework but unvalued may be a real device (view_sheet it), a bare tag is probably a note mention. Marks default to the set's schedule row keys (a compound row "R1 / E1" answers for R1 AND E1; each mark cites its row), or state them: {marks: ["S1","R1"]}. The complement to sweep_schedule_row: THAT tool is for marks drawn ON their marker with no value (finish tags in bubbles) and matches geometry; this one is for annotated devices and needs no fingerprint at all. Refusal-honest: scans refuse (no text layer), a set with no mark-shaped rows refuses unless marks are stated, non-plan sheets are skipped with the role that excused them. commit: true commits every counted occurrence under its mark's own tag — ONE undo step for the whole census, schedule citation on origin. Counts are scale-free (EA) — no set_scale needed. Then AUDIT: view_sheet {overlay: true} where the markers landed, and read every withheld entry — a withheld item you ignore is a hole in the bid. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt. EQUIPMENT marks (a row in an equipment/device schedule — fans, pumps, heaters, fixtures, panels) follow the leader-tag convention instead: a scheduled mark drawn amid linework with no value under it is counted BY LABEL (occurrence by: "label", counted_by_label on the mark); a bare mention in a note still withholds.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "commit": {
      "default": false,
      "description": "Commit every counted occurrence as one EA count marker under its mark (withheld/excluded never commit)",
      "type": "boolean"
    },
    "marks": {
      "description": "The marks to census, e.g. [\"S1\", \"R1\"] — omit to take them from the schedule tables' row keys",
      "items": {
        "minLength": 1,
        "type": "string"
      },
      "type": "array"
    }
  },
  "type": "object"
}
sha256:b19ba5574150fc7d09c8c98d2d54525c9c524bf5e46aa30cb92e09fd8b797fc4

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "complete": {
      "type": "boolean"
    },
    "excluded_in_tables": {
      "description": "Tag occurrences inside a schedule table's own region — row labels, never instances",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "marks": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "committed": {
            "additionalProperties": false,
            "properties": {
              "committed": {
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "ea_total": {
                "type": "number"
              }
            },
            "required": [
              "committed",
              "ea_total"
            ],
            "type": "object"
          },
          "count": {
            "description": "Instances counted on plan-role sheets — value-paired tags, plus (for an equipment-schedule mark) tags drawn amid linework, see counted_by_label",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "counted_by_label": {
            "description": "…of which counted by label (an equipment mark with a leader, no value under it)",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "mark": {
            "type": "string"
          },
          "occurrences": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "description": "The tag's center (image px)",
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "by": {
                  "description": "\"value\" = tag-over-value (air devices, fixtures); \"label\" = an EQUIPMENT-schedule mark drawn amid linework with no value — the leader-tag convention, counted as one instance and said so",
                  "enum": [
                    "value",
                    "label"
                  ],
                  "type": "string"
                },
                "sheet": {
                  "type": "string"
                },
                "value": {
                  "description": "The paired value drawn under the tag (CFM, GPM, a count — the annotation that makes it an instance); absent when counted by label",
                  "type": "string"
                }
              },
              "required": [
                "at",
                "sheet",
                "by"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "occurrences_elided": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "row": {
            "additionalProperties": false,
            "description": "The schedule row that answers for this mark (a compound key answers for each part)",
            "properties": {
              "key": {
                "type": "string"
              },
              "sheet": {
                "type": "string"
              },
              "table": {
                "type": "string"
              }
            },
            "required": [
              "sheet",
              "key",
              "table"
            ],
            "type": "object"
          },
          "unscheduled": {
            "description": "true when the mark was stated by the caller but no schedule row answers for it",
            "type": "boolean"
          },
          "withheld": {
            "description": "Tag occurrences that did NOT count, each with the reason — read them, look, resolve or report",
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "description": "The tag's center (image px) — view_sheet here",
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "reason": {
                  "type": "string"
                },
                "sheet": {
                  "type": "string"
                }
              },
              "required": [
                "at",
                "sheet",
                "reason"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "withheld_elided": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          }
        },
        "required": [
          "mark",
          "count",
          "occurrences",
          "withheld"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "per_sheet": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "counts": {
            "additionalProperties": {
              "maximum": 9007199254740991,
              "minimum": -9007199254740991,
              "type": "integer"
            },
            "propertyNames": {
              "type": "string"
            },
            "type": "object"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "counts"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "skipped": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "reason": {
            "type": "string"
          },
          "role": {
            "type": "string"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "role",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "total": {
      "description": "All counted instances across every mark",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "marks",
    "total",
    "per_sheet",
    "skipped",
    "complete"
  ],
  "type": "object"
}
sha256:b31fd201b55bd1dd8fed489e06754fa07845c7828e7a8d4757ff25f5c3422a56

Description hash: sha256:e9a5e80a31b6e27093aa9d333c26ce20559542719d69c61ca2b24a5dffdaeb48

Interface hash: sha256:62bc61c61ba1bb6ad9f68be77490ab92a6c548637e451a99691f586c1eab99d6

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/count_marks",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "count_marks"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:09880f5b422fd5e5c9fa4019a40501e466863dd3366c807b29c91b3e74a96d83"
}
toolunknown0.9.990.9.100
create_rfikentucky-ai-opentakeoff:tool:create_rfi
Observed interface and hashes

Raise an RFI — a Request For Information — when the drawing set contradicts itself or cannot answer a question you need answered to take the work off: a room-finish schedule row that names a tag the plan never draws, a room label the schedule has no row for, a finish called out two ways, a scale that disagrees with a stated dimension. It lands in the estimator's RFI register (the canvas's RFI panel) with the next number in that register's own sequence (RFI-001, RFI-002, …), status open, dated today, on the sheet you name. You raise it as the agent: the record carries origin {actor: "agent", reviewed: false} and is PENDING — pencil — until the estimator accepts it in the register, because an RFI goes to the architect and nothing sends without a human. It still prints in the marked set's RFI schedule like any other RFI, so the question is on the deliverable. Pass markup_ids to pin it to annotations already on the sheet (annotate a cloud or callout at the conflict first, then link it here) — a linked markup carries the RFI number on the canvas and in the marked set, and list_rfis reports which finish tags the question touches through those links. Prefer this to describing the conflict in prose: a question in the register is tracked, numbered, and answered; a sentence in a reply is lost. Journaled; undo_last takes it back.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "markup_ids": {
      "description": "Annotation ids (annotate / list_annotations) to link — they carry this RFI's number on the sheet",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "question": {
      "description": "What you are asking the architect to answer, stated so a reply can settle it",
      "type": "string"
    },
    "sheet": {
      "description": "Sheet name or number the question is about, as sheet_info reports it",
      "type": "string"
    },
    "title": {
      "description": "The one-line subject the register and the RFI schedule print — what the question is about",
      "type": "string"
    }
  },
  "required": [
    "title",
    "question",
    "sheet"
  ],
  "type": "object"
}
sha256:a918a3501f7e4af4ad323767b0d108bd6ca476e3747a65692a79050649168974

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "actor": {
      "description": "Who raised it — \"agent\" for every RFI minted over MCP, \"estimator\" for a panel-raised one",
      "enum": [
        "agent",
        "estimator"
      ],
      "type": "string"
    },
    "conditions": {
      "description": "Finish tags the linked markups are attached to — the scopes this question touches",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "date": {
      "description": "YYYY-MM-DD opened",
      "type": "string"
    },
    "id": {
      "description": "The record id (\"rfi-…\")",
      "type": "string"
    },
    "linked_markups": {
      "description": "Annotation ids carrying this RFI's number on the sheet (markup.rfi_id) — derived, never stored twice",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "note": {
      "type": "string"
    },
    "number": {
      "description": "The register number, \"RFI-001\" — next in the panel's own sequence, never reissued",
      "type": "string"
    },
    "pending": {
      "description": "true = agent-raised and not yet accepted by an estimator in the register (origin.reviewed false) — pencil, not sent",
      "type": "boolean"
    },
    "question": {
      "type": "string"
    },
    "response": {
      "type": "string"
    },
    "response_date": {
      "description": "YYYY-MM-DD answered, '' while open",
      "type": "string"
    },
    "sheet": {
      "description": "The sheet the question is about",
      "type": "string"
    },
    "status": {
      "description": "The panel's lifecycle: open → answered → closed; void = withdrawn",
      "enum": [
        "open",
        "answered",
        "closed",
        "void"
      ],
      "type": "string"
    },
    "subject": {
      "type": "string"
    }
  },
  "required": [
    "id",
    "number",
    "subject",
    "question",
    "status",
    "sheet",
    "actor",
    "pending",
    "date",
    "response",
    "response_date",
    "linked_markups",
    "conditions",
    "note"
  ],
  "type": "object"
}
sha256:df4e46c56171414dd8c1f90ed1e78db756dfb4456b17bedfd1fe8701d0ff8940

Description hash: sha256:172acae56a94e869497fde03cae0df161d81f33d112633444b829cdfa4219508

Interface hash: sha256:4e01bed430268b3e783678768456d10e380ad7230f71a37244301934cfdd93cd

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/create_rfi",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "create_rfi"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:6f8a8a0a732c274ab7e65d9ab3e838b11b658038bc197e5a09dfdf7460ba1d43"
}
toolwrite0.9.990.9.100
cut_outkentucky-ai-opentakeoff:tool:cut_out
Observed interface and hashes

Cut a REAL hole in a committed floor_area shape (#206) — the way the canvas cuts one (#137): the same lib/cutout.js boolean subtract, so the two surfaces can never disagree about what a hole holds. The parent keeps its outer ring plus the reconciled hole(s) (verts_norm_holes), its computed nets for real — N cuts compose, overlap between cuts never double-deducts (set subtraction), a hole ADDS perimeter — and the deduct commits carrying cuts_shape_id so the report and legend read the reconciled number, never a second arithmetic pass. This is the verb for a column, a floor drain, an island of casework INSIDE a room; an independent measure_polygon role:"deduct" stays the tool for a deduction that isn't a hole in one parent. Refusal over guessing: the ring must sit FULLY inside the parent's outer ring (an edge-crossing cut is a boundary correction — edit_shape the parent instead), and a cut that would erase the parent or split it in two refuses whole (trace the pieces as rooms). One journal entry — undo_last restores parent and hole together; delete_shape on the deduct later reverts the cut too (a multi-cut parent rebuilds from the chain's pristine snapshot minus the survivors). AN OPEN RUN IS CLIPPED, NOT SUBTRACTED: wall tile (surface_area) and base/transitions (linear) are polylines traced in plan, so the ring removes the stretch it covers, the run keeps its id and takes what survives, and a cut through the MIDDLE leaves the far side as its own shape (same condition, same height) — quantities ride the surviving length, which is exact, since wall SF is LF × height and a border's SF is LF × thickness. No deduct is minted for a run: there is no area for one to sit on, and a deduct's SF counts against the FLOOR total a run never fills. A ring that misses the run, one that swallows it whole (delete_shape it), and a curved run (its verts are control points) all refuse. A derived base with numeric openings also refuses: those deductions have no stored location; use measure_line for installed runs so a geometric cut cannot erase the numeric allowance. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "parent_shape_id": {
      "description": "A committed floor_area shape id, or an open run (surface_area / linear) to clip (list_shapes)",
      "type": "string"
    },
    "verts": {
      "description": "The ring, image px — fully inside the parent for an area; over the stretch to remove for a run",
      "items": {
        "additionalItems": false,
        "items": [
          {
            "type": "number"
          },
          {
            "type": "number"
          }
        ],
        "maxItems": 2,
        "minItems": 2,
        "type": "array"
      },
      "minItems": 3,
      "type": "array"
    }
  },
  "required": [
    "parent_shape_id",
    "verts"
  ],
  "type": "object"
}
sha256:4a60a9a2986b960e547b427b9eb2904eddbc01219930804ae5464ff2f0e184fd

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "deduct_shape_id": {
      "description": "Area parent: the reconciled deduct — carries cuts_shape_id; totals skip it (the parent nets the hole)",
      "type": "string"
    },
    "hole_sf": {
      "description": "Area parent: what this cut actually removed from the parent's net — 0 when the ring fell entirely inside an existing hole",
      "type": "number"
    },
    "holes": {
      "description": "Area parent: holes the parent now carries",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "measure_role": {
      "description": "Run parent: surface_area or linear",
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "parent_net": {
      "additionalProperties": false,
      "properties": {
        "area_sf": {
          "description": "The parent's recomputed net after the subtract",
          "type": "number"
        },
        "perimeter_lf": {
          "description": "Outer ring + hole boundaries — a hole ADDS perimeter",
          "type": "number"
        }
      },
      "required": [
        "area_sf",
        "perimeter_lf"
      ],
      "type": "object"
    },
    "parent_shape_id": {
      "type": "string"
    },
    "pieces": {
      "description": "Run parent: every stretch that survived the cut — more than one when the ring fell in the middle",
      "items": {
        "additionalProperties": false,
        "properties": {
          "lf": {
            "description": "This piece's own length",
            "type": "number"
          },
          "sf": {
            "description": "LF × the height (wall) or the thickness (border) it was measured at",
            "type": "number"
          },
          "shape_id": {
            "type": "string"
          }
        },
        "required": [
          "shape_id",
          "lf",
          "sf"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "removed_lf": {
      "description": "Run parent: length the cut took out",
      "type": "number"
    },
    "removed_sf": {
      "description": "Run parent: the SF that rode on that length",
      "type": "number"
    },
    "shape_id": {
      "description": "Run parent: the run that was clipped — it keeps its id and takes the first surviving stretch",
      "type": "string"
    }
  },
  "required": [
    "note"
  ],
  "type": "object"
}
sha256:2c1c4d5b8c452cfbb8cf7b65edebfe1e46cf2346ea023b73fd572f9961bc0f73

Description hash: sha256:ecc2269412da1ced021f6a7953d97df30a06efb337d98e35bec953188247588d

Interface hash: sha256:24f7aef83be2532aab59b616f22b9b1679e3534044d140c7c72176b4381538a1

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/cut_out",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "cut_out"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:97a7efe9497e3165ef80d935dc8f5242e374a656185fbe04e3f91c9213d475f4"
}
toolunknown0.9.990.9.100
delete_rfikentucky-ai-opentakeoff:tool:delete_rfi
Observed interface and hashes

Withdraw an RFI. A TOMBSTONE, never a renumber: the record stays with its number reserved, so the register and the marked set keep printing a gap where it was and the next RFI takes the next number — an RFI number that went out and then meant something else would be a lie. Every markup linked to it keeps its note and loses the link (the canvas's own delete rule). Withdraw a question you raised in error; a question the architect answered is closed in the register, not deleted. Journaled; undo_last puts the record and its links back.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "rfi_id": {
      "description": "Record id from create_rfi or list_rfis",
      "type": "string"
    }
  },
  "required": [
    "rfi_id"
  ],
  "type": "object"
}
sha256:b4a65ae5d90aabac953b9e373d8f58500f90f725ec7ee6023a2787daefe56cd6

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "deleted": {
      "description": "The withdrawn record's id",
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "number": {
      "description": "Its number — stays reserved; the register and the marked set keep the gap",
      "type": "string"
    },
    "rfis_remaining": {
      "description": "Live RFIs after the withdrawal",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "unlinked_markups": {
      "description": "Markups that kept their note and lost the link",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "deleted",
    "number",
    "unlinked_markups",
    "rfis_remaining",
    "note"
  ],
  "type": "object"
}
sha256:8f5cc7faac7ad7266eb494b7888b224ab8b062c4195da322b168ab46be6932cc

Description hash: sha256:432f4915e8976aa181780df4890002d58078ddb0d0da5128757bcc3bbe6190d0

Interface hash: sha256:a84cbb363c6df73d06ae6671ba186206284af85cce86086dd5a6e19fdd6dd836

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/delete_rfi",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "delete_rfi"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:a5eba0b4eb51ef8e99c22a6f891b3a31cc7ef31dcec997d7b7a3adcc433c22f8"
}
tooldestructive0.9.990.9.100
delete_shapekentucky-ai-opentakeoff:tool:delete_shape
Observed interface and hashes

Remove a committed shape by the id returned when it was committed. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "shape_id": {
      "type": "string"
    }
  },
  "required": [
    "shape_id"
  ],
  "type": "object"
}
sha256:12e9c75ca66608e82410bc2e38d031e38c349fc5768d46eaae4f63be5ad8561d

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "deleted": {
      "description": "The removed shape's id",
      "type": "string"
    },
    "note": {
      "description": "Cutout interplay (#206), when it applies: the parent's cut was reverted, could not be rebuilt, or reconciled deducts were orphaned by a parent delete",
      "type": "string"
    },
    "shape_count": {
      "description": "Committed shapes remaining",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "deleted",
    "shape_count"
  ],
  "type": "object"
}
sha256:8f421e9079febf32f23c68d174f28dd1dcc3279b513cd3092677290ccb8a26c5

Description hash: sha256:e4ec3fd922eeab49790cd464a386e8ee360b6367e4b169d7bf41d350efb7ff89

Interface hash: sha256:aa0152917192beecd4f0ee127d6cc03556c382d476a9103946d2b097e8be2a37

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/delete_shape",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "delete_shape"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:c16548ce7282431f9bb160d1ff4420158af83c8c963080b4fc5a21a4aff47b10"
}
tooldestructive0.9.990.9.100
delete_verdictkentucky-ai-opentakeoff:tool:delete_verdict
Observed interface and hashes

Lift an agent verdict mark by id (mark_verdict's reply, or list_annotations verdicts[]). Agent marks only: the estimator's APPROVED seal is human ink and is refused — the same line edit_shape holds on reviewed shapes. Journaled like every mutation, so undo_last re-seats a lifted mark exactly where it was.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "verdict_id": {
      "description": "Record id from mark_verdict or list_annotations verdicts[]",
      "type": "string"
    }
  },
  "required": [
    "verdict_id"
  ],
  "type": "object"
}
sha256:c0ee89eae54d63c949a9f46208e2491464d99d2963d579da574523fb2858ce11

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "deleted": {
      "description": "The lifted record's id",
      "type": "string"
    },
    "verdicts_remaining": {
      "description": "Approval-family records still on the takeoff (both actors)",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "deleted",
    "verdicts_remaining"
  ],
  "type": "object"
}
sha256:f3c16b9da518eaa24103cd3175dc27a019660e95d34d7312a1587ebc3fe60033

Description hash: sha256:d96ae99c7d1b5a2e44b44cc33203f6e0023fdae4c85b597486369401e62f134d

Interface hash: sha256:ca68ff15edb8579c8dfef843049fc3483bdd1ea33e8b87dbedfdad988f0306f3

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/delete_verdict",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "delete_verdict"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:5cb1dd39aa45ffaa3d467635ea35f7302d1bebcb08dbf2435ac6714618601b31"
}
toolunknown0.9.990.9.100
derive_basekentucky-ai-opentakeoff:tool:derive_base
Observed interface and hashes

Mint the wall base from committed rooms (#148) — the estimator's most mechanical derivation: base LF = room perimeter − stated door openings. For every floor_area shape of source_condition, commits ONE linear shape under condition (e.g. 'RB-1') tracing that room's boundary, quantified NET of the openings you state per room. The openings are YOUR claim to make — look at the doors with view_sheet, state {shape_id, lf} per room (repeat a shape_id to stack openings); the tool never guesses, and your claim is recorded on origin.derived (from_shape_id, gross_lf, openings_lf). The output geometry remains the whole perimeter: deducted openings are numerical, not visible gaps. For a drawing of the actual installed base, use measure_line on the physical runs after checking door jambs, alcoves and open finish splits. All-or-nothing: an unknown shape_id, a negative lf, or openings meeting a room's whole perimeter refuses the call before anything commits. The whole derivation is ONE undo step. Deriving onto the source condition is refused — base lands on its own tag.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Finish tag the base commits under (minted on first use), e.g. 'RB-1'",
      "type": "string"
    },
    "openings": {
      "description": "Stated openings per room — omit for gross perimeters",
      "items": {
        "properties": {
          "lf": {
            "description": "Door/opening width to deduct from that room's perimeter, in feet",
            "minimum": 0,
            "type": "number"
          },
          "shape_id": {
            "description": "A floor_area shape id of source_condition (list_shapes)",
            "type": "string"
          }
        },
        "required": [
          "shape_id",
          "lf"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "source_condition": {
      "description": "Finish tag whose floor_area rooms the base derives from, e.g. 'CPT-1'",
      "type": "string"
    }
  },
  "required": [
    "source_condition",
    "condition"
  ],
  "type": "object"
}
sha256:2c77724548284890c6686adbed3962235bb1472d9357889099633b60b92c25d7

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "committed": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "condition": {
      "description": "The tag the base committed under",
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "rooms": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "base_shape_id": {
            "description": "The committed linear base shape",
            "type": "string"
          },
          "gross_lf": {
            "description": "The room's full perimeter",
            "type": "number"
          },
          "net_lf": {
            "description": "gross − openings — the committed quantity",
            "type": "number"
          },
          "openings_lf": {
            "description": "The openings you stated for this room",
            "type": "number"
          },
          "sheet": {
            "type": "string"
          },
          "source_shape_id": {
            "type": "string"
          }
        },
        "required": [
          "source_shape_id",
          "base_shape_id",
          "sheet",
          "gross_lf",
          "openings_lf",
          "net_lf"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "source_condition": {
      "type": "string"
    },
    "total_lf": {
      "description": "Sum of net_lf across rooms",
      "type": "number"
    }
  },
  "required": [
    "condition",
    "source_condition",
    "rooms",
    "committed",
    "total_lf",
    "note"
  ],
  "type": "object"
}
sha256:550529630ec55648c93454f4528e4ea02c825fae7f28fe68d1103cbfc1a89233

Description hash: sha256:3f6cfc454bab4619f1601256153081312213e9807640fc756a2060560f3d81c6

Interface hash: sha256:b0253b11f9d04683763ced203eb8441a111a7dd2f52591b1a8242ee101c0854a

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/derive_base",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "derive_base"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:e8be4653b341938b3d2113e7bb5435aecf3fb3e6347717f55d9d769b8e032744"
}
toolunknown0.9.990.9.100
derive_transitionskentucky-ai-opentakeoff:tool:derive_transitions
Observed interface and hashes

Mint the transition where two finishes MEET (#202) — the derivation that follows derive_base, and the line an estimator draws by hand on every job. Pass the two finish tags and the tag the transition commits under (e.g. condition_a 'CPT-1', condition_b 'PT-1', condition 'T-1'), and every committed room of each is compared against every committed room of the other. WHAT THE GEOMETRY ACTUALLY IS, because it decides what you get back: flood-traced rooms DO NOT SHARE EDGES. A trace fills to the wall linework, so two rooms across a partition are separated by four to eight inches of nothing — testing for a shared edge finds zero transitions on a real planset. What is there is proximity, in two flavours that mean completely different things: • BUTT JOINT — the two rings run together inside ONE open space (a lobby that changes from carpet to tile with no wall between). The transition IS that run, and it commits as a linear shape under your tag, origin.derived naming both parent shapes and the measured gap. • WALL-SEPARATED — the rings run parallel across a partition. The rooms are adjacent, but the transition is NOT the shared wall: it is a threshold, in the doorway, and NOTHING in the trace record says where the doorway is (the flood engine seals openings and reports how MUCH boundary it synthesised, never where). Committing 34 LF of threshold because two rooms share 34 LF of wall would be a wrong bid with a machine's confidence behind it. These come back in `withheld` — measured, with their length, their gap in inches, and an `at` point — as questions you answer by LOOKING (view_sheet at `at`, then measure_line or place_count the threshold yourself). The symbol_sweep doctrine: a near-match is never a silent commit and never a silent drop. Tuning: max_gap_in (default 12) is how far apart two rings can be and still count as adjacent at all — raise it for thick walls, and every extra inch turns more of the plan into wall_separated questions, never into committed LF. min_run_in (default 12) drops corner artifacts. The butt-joint threshold is fixed at one inch and is not a knob: "these two finishes touch" is not a judgement call. All-or-nothing, like derive_base: an unknown tag, a transition landing on either source tag, the same tag twice, or a sheet without a scale refuses the whole call before anything commits. The whole sweep is ONE undo step. After it, LOOK — view_sheet {overlay: true} over each run — before trusting total_lf. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Finish tag the transitions commit under (minted on first use), e.g. 'T-1'. Must differ from both sources",
      "type": "string"
    },
    "condition_a": {
      "description": "First finish tag, e.g. 'CPT-1' — its committed rooms are walked, and runs are traced along their boundaries",
      "type": "string"
    },
    "condition_b": {
      "description": "Second finish tag, e.g. 'PT-1'",
      "type": "string"
    },
    "max_gap_in": {
      "description": "How far apart two rings can be and still count as adjacent, in inches (default 12 — a thick partition). Wider only produces more wall_separated QUESTIONS, never more committed LF",
      "exclusiveMinimum": 0,
      "type": "number"
    },
    "min_run_in": {
      "description": "Shortest run worth reporting, in inches (default 12) — below this is a corner where two rooms clip, not a transition",
      "exclusiveMinimum": 0,
      "type": "number"
    }
  },
  "required": [
    "condition_a",
    "condition_b",
    "condition"
  ],
  "type": "object"
}
sha256:f1fb9f829ae427e277ff72f882f04c61219bc43818fd3602a33cbf402fae509c

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "between": {
      "description": "The two finish tags",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "committed": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "condition": {
      "description": "The tag the transitions committed under",
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "runs": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "at": {
            "description": "Run midpoint (image px) — pass to view_sheet to look at it",
            "items": {
              "type": "number"
            },
            "type": "array"
          },
          "between_shape_ids": {
            "description": "The two floor_area shapes this run separates",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "gap_in": {
            "description": "Median distance between the two rings across the run, in inches — 0-ish is one open space, 4-8 is a partition",
            "type": "number"
          },
          "length_lf": {
            "description": "Run length along the first shape's boundary",
            "type": "number"
          },
          "shape_id": {
            "type": "string"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "between_shape_ids",
          "length_lf",
          "gap_in",
          "at",
          "shape_id"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "total_lf": {
      "description": "Sum of committed run lengths — butt joints only",
      "type": "number"
    },
    "withheld": {
      "description": "Adjacency across a wall: real, measured, and NOT committed — the transition there is a threshold at a doorway this cannot locate",
      "items": {
        "additionalProperties": false,
        "properties": {
          "at": {
            "description": "Run midpoint (image px) — pass to view_sheet to look at it",
            "items": {
              "type": "number"
            },
            "type": "array"
          },
          "between_shape_ids": {
            "description": "The two floor_area shapes this run separates",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "detail": {
            "type": "string"
          },
          "gap_in": {
            "description": "Median distance between the two rings across the run, in inches — 0-ish is one open space, 4-8 is a partition",
            "type": "number"
          },
          "length_lf": {
            "description": "Run length along the first shape's boundary",
            "type": "number"
          },
          "reason": {
            "const": "wall_separated",
            "type": "string"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "between_shape_ids",
          "length_lf",
          "gap_in",
          "at",
          "reason",
          "detail"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "withheld_lf": {
      "description": "Shared-wall length held back — never part of total_lf",
      "type": "number"
    }
  },
  "required": [
    "condition",
    "between",
    "committed",
    "total_lf",
    "runs",
    "withheld",
    "withheld_lf",
    "note"
  ],
  "type": "object"
}
sha256:a6c5bdc01438e340752ae8427030f44ab4a02b19a4a46e145462580cb4555522

Description hash: sha256:ea1fa5edb74f47594e575218aad675c92299b07d68fbbbef84f6b5e9098c33bd

Interface hash: sha256:4f45fa78d2339199932d2f641cd277f62e689964b9b23d9f79b8bd018cd6eecf

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/derive_transitions",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "derive_transitions"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:6cb2b32117739f4de300a4432d8291afd03502430b1575279beb956661e82646"
}
toolunknown0.9.990.9.100
duplicate_conditionkentucky-ai-opentakeoff:tool:duplicate_condition
Observed interface and hashes

Twin a condition — the same finish measured somewhere else, with its own supporting materials. One finish in two areas is not two conditions and it is not one either: the same sheet goods over a slab and over a raised deck take the same field material and different preparation underneath (one wants a moisture barrier, the other a primer and a different adhesive). The twin arrives carrying the original's whole materials list and keeps FOLLOWING it — change a coverage rate on the original and every twin that has not touched that row gets it; edit a row on the twin and only THAT row stops following. `label` is REQUIRED and becomes the tag suffix ('CPT-1' + 'Level 2' → 'CPT-1 – Level 2'), because every tool in this server resolves a condition by finish tag and takes the FIRST match: two conditions sharing a tag would make one permanently unreachable, and a takeoff re-import collapses them last-wins. A label already in use is refused rather than de-collided. No takeoffs come along — measure the new area against the returned condition_id. Reversible with undo_last; use split_condition to end the inheritance permanently.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Finish tag of the condition to twin, e.g. 'CPT-1'",
      "type": "string"
    },
    "label": {
      "description": "What makes this one different, usually the area: 'Level 2', 'Building B', 'Phase 2'",
      "type": "string"
    }
  },
  "required": [
    "condition",
    "label"
  ],
  "type": "object"
}
sha256:39448eae35c860d0919a89b2eaa802f970bdd37138cd29a0abcf31902292fa0e

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "condition": {
      "description": "The twin's finish tag — base tag + the label, e.g. 'CPT-1 – Level 2'",
      "type": "string"
    },
    "condition_id": {
      "description": "The TWIN — measure the new area against this",
      "type": "string"
    },
    "family_id": {
      "description": "Shared by every variant of this finish — survives a split",
      "type": "string"
    },
    "inherited_rows": {
      "description": "Material rows copied, all still following the original",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "note": {
      "type": "string"
    },
    "variant_label": {
      "type": "string"
    },
    "variant_of": {
      "description": "The condition whose material rows this one follows",
      "type": "string"
    }
  },
  "required": [
    "condition",
    "condition_id",
    "variant_of",
    "variant_label",
    "family_id",
    "inherited_rows",
    "note"
  ],
  "type": "object"
}
sha256:19956ca71565f093b285a8a20698b327047cb4040dbf7f11e59b72b4e61ec6d1

Description hash: sha256:155433f98c2759434f45617e4c797f03f3dd06d30482c7bef76e86efce52e8bf

Interface hash: sha256:3a78e0fc2b7475336180b97a553f28ebbbc67d11892138c93ba97fc62ef5abe4

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/duplicate_condition",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "duplicate_condition"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:9bfa795a3f6376864286b539b96e8702a035a049f5b774ee304b72ea441cf09b"
}
toolunknown0.9.990.9.100
edit_annotationkentucky-ai-opentakeoff:tool:edit_annotation
Observed interface and hashes

Shorten, replace or clear the text of an existing annotation. Get annotation_id from list_annotations (annotations, not verdicts). Changes only text: position, shape, dimension length, condition links, quantities and review records stay unchanged. Empty text clears the note; a dimension still prints its measured length. Refuses an RFI-linked note: review that question's context in the browser RFI register. One undo_last step restores the previous text. Does not create a verdict or human approval.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "annotation_id": {
      "description": "An annotation id from list_annotations",
      "type": "string"
    },
    "text": {
      "description": "Replacement text; empty string clears it",
      "type": "string"
    }
  },
  "required": [
    "annotation_id",
    "text"
  ],
  "type": "object"
}
sha256:77ed26ed45a610402221e65411dd475c4e4af1c2e3bfa291e3ca40a4870072ef

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "id": {
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "text": {
      "type": "string"
    }
  },
  "required": [
    "id",
    "text",
    "note"
  ],
  "type": "object"
}
sha256:513d91a88e0b68fccdf7a2a6b210af530b8f994fb486e51b15472becca139ffe

Description hash: sha256:902707e96848948d587587ea387c572270ea5f634b2d46eb5afc50d7b27997c3

Interface hash: sha256:aceefb1107a7ff2bb2fa6700766676922720c733d9470d1750d9a5aa2a8a3a41

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/edit_annotation",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "edit_annotation"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:5d4514a25950eeb216da3f176ed45a8efe775033bfd805b2b8fd159d84819967"
}
toolwrite0.9.990.9.100
edit_conditionkentucky-ai-opentakeoff:tool:edit_condition
Observed interface and hashes

Set a condition's quantity knobs — waste %, multiplier, height_ft (the H knob measure_surface quantifies against), and/or roll_setup (the roll-goods opt-in: seams and order footage figured from the committed rooms, #147). takeoff_summary emits waste-adjusted *_net order quantities and a per-condition multiplier, and every export carries both, but conditions minted through the measure tools start at waste 0 / multiplier 1 — without this tool an agent's takeoff always ships net === gross (#131). waste_pct is the estimator's cut-waste percentage (carpet commonly 5–10); multiplier scales every quantity on the condition (×N identical floors — takeoff_summary applies it before waste). condition must resolve to an EXISTING finish tag — a typo'd tag errors rather than minting an empty condition (the edit_materials remove/patch rule, not its add rule: these knobs mean nothing on a condition that doesn't exist yet). No review gate — quantity config, not traced geometry; undo_last reverses a call in one step (both knobs snapshotted together, restored verbatim).

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Finish tag of an existing condition, e.g. 'CPT-1'",
      "type": "string"
    },
    "drop_ft": {
      "description": "Drop and Rise (#441): the vertical leg DOWN, in feet, every linear run of this condition adds to its plan length. Re-flows existing runs that do not carry their own drop_ft. 0 turns it off",
      "minimum": 0,
      "type": "number"
    },
    "height_ft": {
      "description": "Wall height in feet — the canvas's H knob; measure_surface quantifies traced LF × this",
      "exclusiveMinimum": 0,
      "type": "number"
    },
    "multiplier": {
      "description": "Quantity multiplier (×N identical areas). Note: the canvas treats 0 as 1, so 0 is rejected here rather than silently meaning 'off'",
      "exclusiveMinimum": 0,
      "type": "number"
    },
    "rise_ft": {
      "description": "Drop and Rise (#441): the vertical leg UP, in feet, every linear run of this condition adds to its plan length (LF = plan + rise + drop). Re-flows existing runs that do not carry their own rise_ft; derived base/transitions never take a leg. 0 turns it off",
      "minimum": 0,
      "type": "number"
    },
    "roll_setup": {
      "anyOf": [
        {
          "description": "Opt the condition OUT of roll goods",
          "type": "null"
        },
        {
          "properties": {
            "direction": {
              "description": "Run direction; auto lets the engine pick per room",
              "enum": [
                "auto",
                "ns",
                "ew"
              ],
              "type": "string"
            },
            "doorway_overage_in": {
              "minimum": 0,
              "type": "number"
            },
            "material": {
              "description": "Material class — fresh opt-ins and material changes start from this class's engine defaults (carpet sells sy, others sf)",
              "enum": [
                "carpet",
                "sheet_vinyl",
                "rubber"
              ],
              "type": "string"
            },
            "price_unit": {
              "description": "Sell unit the order quantity is figured in",
              "enum": [
                "sy",
                "sf",
                "lf"
              ],
              "type": "string"
            },
            "roll_length_ft": {
              "description": "Physical roll length; 0 = unlimited",
              "minimum": 0,
              "type": "number"
            },
            "roll_width_ft": {
              "exclusiveMinimum": 0,
              "type": "number"
            },
            "seam_allowance_in": {
              "minimum": 0,
              "type": "number"
            },
            "wall_overage_in": {
              "minimum": 0,
              "type": "number"
            }
          },
          "type": "object"
        }
      ],
      "description": "Roll-goods opt-in (#147): presence of a setup is what makes the condition roll goods — seams figured, cuts packed, order footage beside the measured quantities. Same-material partial edits patch the existing setup; null opts out. The reply echoes the figured order (cuts, order_lf, rolls, order_qty) whenever floor shapes exist on scaled sheets, and export_report's roll_goods block carries the same rows"
    },
    "waste_pct": {
      "description": "Waste percentage applied to net order quantities, e.g. 10 for 10%",
      "minimum": 0,
      "type": "number"
    }
  },
  "required": [
    "condition"
  ],
  "type": "object"
}
sha256:251df0ccbb55a645fbc50cf16b3c63281009737726882c682470a4f56af32963

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "condition": {
      "description": "The finish tag passed in",
      "type": "string"
    },
    "condition_id": {
      "type": "string"
    },
    "drop_ft": {
      "description": "The condition's default drop for its linear runs after this write — present once set (#441)",
      "type": "number"
    },
    "height_ft": {
      "description": "The condition's wall height after this write — present once set (measure_surface multiplies traced LF by it)",
      "type": "number"
    },
    "multiplier": {
      "description": "The condition's quantity multiplier after this write",
      "type": "number"
    },
    "rise_ft": {
      "description": "The condition's default rise for its linear runs after this write — present once set (#441)",
      "type": "number"
    },
    "roll": {
      "additionalProperties": {},
      "description": "The figured order (same row export_report's roll_goods carries) — present when the roll-goods condition has floor shapes on scaled sheets",
      "properties": {
        "condition_id": {
          "type": "string"
        },
        "cuts": {
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "direction": {
          "type": "string"
        },
        "finish_tag": {
          "type": "string"
        },
        "material": {
          "type": "string"
        },
        "order_lf": {
          "description": "Full-width roll footage to order, ×N applied, rounded up to the inch",
          "type": "number"
        },
        "order_qty": {
          "type": "number"
        },
        "order_unit": {
          "type": "string"
        },
        "oversize": {
          "description": "true when a cut exceeds the physical roll length (roll_length_ft binds)",
          "type": "boolean"
        },
        "roll_length_ft": {
          "type": "number"
        },
        "roll_width_ft": {
          "type": "number"
        },
        "rolls": {
          "type": "number"
        }
      },
      "required": [
        "condition_id",
        "finish_tag",
        "material",
        "roll_width_ft",
        "roll_length_ft",
        "direction",
        "cuts",
        "order_lf",
        "rolls",
        "order_qty",
        "order_unit",
        "oversize"
      ],
      "type": "object"
    },
    "roll_setup": {
      "additionalProperties": {},
      "description": "The condition's roll-goods setup after this write — present while opted in",
      "properties": {},
      "type": "object"
    },
    "waste_pct": {
      "description": "The condition's waste % after this write",
      "type": "number"
    }
  },
  "required": [
    "condition",
    "condition_id",
    "waste_pct",
    "multiplier"
  ],
  "type": "object"
}
sha256:f8ae03f660b7ba4027ea4e4db87054f4c7943251806d18ab40412d22200d7e56

Description hash: sha256:48154f043b7fb85896e234df98af3dfdff3a8edb2bf0a24f9e7fc6dd35367884

Interface hash: sha256:cd94c6497c6db46d345e9e81e2ccfc76ed5debf1933c379980702d1a0a73bfb3

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/edit_condition",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "edit_condition"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:c0c64581ef73fd277fc57fe8fc1760fffd8e86c147ac96121abd9112cc340837"
}
toolwrite0.9.990.9.100
edit_materialskentucky-ai-opentakeoff:tool:edit_materials
Observed interface and hashes

Add, remove, or patch supporting-materials rows on a condition — the coverage-rate lines that turn a measured area/length/count into an order quantity (adhesive at N sf/gal, grout at N lf/bag, …), matching the canvas's per-condition Supporting Materials panel. Each row is {name, per, basis, unit, round, note}: quantity = the condition's basis total (area/linear/count/seam_lf) ÷ per, rounded up to whole purchase units unless round:false. basis "seam_lf" is the one basis that is FIGURED rather than measured: it is the length where two cuts meet on the floor, read off the condition's roll layout (set roll_setup with edit_condition), which is what a heat-weld rod or a carpet seam tape is bought by. A 20-ft-wide room off a 12-ft roll seams once down its length; the same square footage as two 10-ft rooms seams not at all, and no percentage of the area or the perimeter can tell those two jobs apart. Without a roll_setup — or with no committed floor shapes to lay out — a seam_lf row reads 0, which is the honest state rather than a guess. condition names an existing OR NEW finish tag (minted on first touch, same as measure_polygon) — add alone is enough to seed materials on a condition before you've traced anything. remove/patch target existing row ids from this reply or export_takeoff (takeoff_summary strips materials for a compact quantities-only reply); a bad id 404s the WHOLE call before anything is written, and referencing an id on a tag with no condition yet errors rather than silently minting an empty one. No review gate here — materials rows are quantity config, not traced geometry, so this edits directly; undo_last reverses a call in one step (the condition's whole materials array, snapshotted before the write, restored verbatim).

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "add": {
      "description": "New rows to add",
      "items": {
        "properties": {
          "basis": {
            "description": "Which of the condition's totals this row divides against — default 'area' (total SF). 'seam_lf' is the figured roll-layout seam length (weld rod, seam tape), 0 until the condition carries a roll_setup",
            "enum": [
              "area",
              "linear",
              "count",
              "seam_lf"
            ],
            "type": "string"
          },
          "name": {
            "minLength": 1,
            "type": "string"
          },
          "note": {
            "type": "string"
          },
          "per": {
            "description": "Coverage rate — basis units per purchase unit, e.g. 250 for 1 gal / 250 sf. Default 0 (quantity 0 until set)",
            "minimum": 0,
            "type": "number"
          },
          "round": {
            "description": "Round up to whole purchase units — default true",
            "type": "boolean"
          },
          "unit": {
            "description": "Purchase unit, e.g. 'gal', 'bag', 'roll'",
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "condition": {
      "description": "Finish tag, e.g. 'CPT-1'",
      "type": "string"
    },
    "patch": {
      "description": "Field changes on existing rows",
      "items": {
        "properties": {
          "fields": {
            "additionalProperties": {
              "type": [
                "string",
                "number",
                "boolean"
              ]
            },
            "description": "Field:value pairs — name/per/basis/unit/round/note only",
            "propertyNames": {
              "type": "string"
            },
            "type": "object"
          },
          "id": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "fields"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "remove": {
      "description": "Existing row ids to remove",
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "condition"
  ],
  "type": "object"
}
sha256:e481d6a283c8d14fcfa6b5db5c98cd9fe644fb26f89c1dc41827b50d7e5f665d

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "changed": {
      "additionalProperties": false,
      "properties": {
        "added": {
          "description": "Ids of newly added rows",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "patched": {
          "description": "Ids whose fields changed",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "removed": {
          "description": "Ids removed",
          "items": {
            "type": "string"
          },
          "type": "array"
        }
      },
      "required": [
        "added",
        "removed",
        "patched"
      ],
      "type": "object"
    },
    "condition": {
      "description": "The finish tag passed in",
      "type": "string"
    },
    "condition_id": {
      "type": "string"
    },
    "materials": {
      "description": "The condition's full materials array after this write",
      "items": {
        "additionalProperties": false,
        "properties": {
          "basis": {
            "description": "Which of the condition's totals this row's quantity is computed against — 'seam_lf' is the FIGURED roll-layout seam length (weld rod, seam tape), 0 until the condition carries a roll_setup",
            "enum": [
              "area",
              "linear",
              "count",
              "seam_lf"
            ],
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "inherited": {
            "description": "On a twin: true while the row still follows the family — a patch on it takes it local, split_condition freezes them all",
            "type": "boolean"
          },
          "name": {
            "type": "string"
          },
          "note": {
            "type": "string"
          },
          "origin_id": {
            "description": "On a twin: the parent row this one follows (the variants.ts family link)",
            "type": "string"
          },
          "per": {
            "description": "Coverage rate: basis ÷ per = order quantity",
            "type": "number"
          },
          "round": {
            "description": "true = round up to whole purchase units (the default — you buy whole bags/buckets)",
            "type": "boolean"
          },
          "unit": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "name",
          "per",
          "basis",
          "unit",
          "round"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "condition",
    "condition_id",
    "changed",
    "materials"
  ],
  "type": "object"
}
sha256:5ea9d3e1504e4b6f26bad3a3b61702163569bb429458e032fe8f13f6da89a508

Description hash: sha256:6b28dd421e4f93deb3268affc80f67ef7be0611f4759399aafeba62debc456be

Interface hash: sha256:441bd3b44ea80df69cfe9e9e48c754a7392a7e7ce428b011391ba3df056b53ba

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/edit_materials",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "edit_materials"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:74e20693e9e9fd7659da2366e4bfe89d3672301ba02bddcaa0ffa3b25e101ed6"
}
toolwrite0.9.990.9.100
edit_shapekentucky-ai-opentakeoff:tool:edit_shape
Observed interface and hashes

REVISE a shape you already committed, instead of deleting it and starting over: pass new verts to move the geometry, condition to reassign it to a different finish tag, role to switch between floor_area / deduct / linear, label to name the room it belongs to, or any combination. Quantities are recomputed from the result — a role flip alone re-measures (closed area vs open length). The loop this is for: measure_polygon to commit, view_sheet with overlay:true to LOOK at what landed, then edit_shape to fix the two vertices that overshot into the corridor. label is the per-room reporting seam: this is how a shape traced by hand — or one whose room number the sweep read wrong — joins the same per-room breakdown the Report and the workbook's floor × room tab group by. Shapes a human affirmed (origin.reviewed) are ink and are refused — an agent revises its own pencil and nothing else. Agent self-revision is tallied on origin.agent_edits, kept deliberately separate from the human-correction fields. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Reassign to this finish tag (minted on first use)",
      "type": "string"
    },
    "drop_ft": {
      "anyOf": [
        {
          "minimum": 0,
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "description": "Linear runs only (#441): this run's vertical leg DOWN in feet, overriding the condition's drop_ft default (0 = none). null clears the override so the condition's default applies again"
    },
    "label": {
      "description": "The room (or phase/area) this shape belongs to, e.g. \"134\" or \"OFFICE 101\" — what per-room reporting groups by. Pass \"\" to clear it",
      "type": "string"
    },
    "rise_ft": {
      "anyOf": [
        {
          "minimum": 0,
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "description": "Linear runs only (#441): this run's vertical leg UP in feet, overriding the condition's rise_ft default (0 = none). null clears the override so the condition's default applies again. perimeter_lf is recomputed as plan + rise + drop"
    },
    "role": {
      "description": "Switch what the shape measures — flipping INTO surface_area needs a height on the shape or its condition",
      "enum": [
        "floor_area",
        "deduct",
        "linear",
        "surface_area",
        "count"
      ],
      "type": "string"
    },
    "shape_id": {
      "description": "Id returned when the shape was committed",
      "type": "string"
    },
    "verts": {
      "description": "Replacement geometry (image px): ≥3 vertices for an area shape, ≥2 points for a linear/surface run, ≥1 for a count marker",
      "items": {
        "additionalItems": false,
        "items": [
          {
            "type": "number"
          },
          {
            "type": "number"
          }
        ],
        "maxItems": 2,
        "minItems": 2,
        "type": "array"
      },
      "type": "array"
    }
  },
  "required": [
    "shape_id"
  ],
  "type": "object"
}
sha256:50879280214f2582ada0dbf0b2af4d66a78d73ba63fc2c0cf2db6ee5a6224735

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "agent_edits": {
      "description": "How many times the agent has revised this shape — separate from the human-correction tally",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "area_sf": {
      "description": "0 for linear shapes; LF × height for surface_area; absent for count",
      "type": "number"
    },
    "changed": {
      "description": "Which fields this call actually changed",
      "items": {
        "enum": [
          "verts",
          "condition",
          "role",
          "label",
          "rise_ft",
          "drop_ft"
        ],
        "type": "string"
      },
      "type": "array"
    },
    "count": {
      "description": "count shapes only — the marker's EA (preserved across the edit)",
      "type": "number"
    },
    "label": {
      "description": "The shape's room/phase label after this call — absent when it carries none (a cleared label reports as absent, not as an empty string)",
      "type": "string"
    },
    "measure_role": {
      "enum": [
        "floor_area",
        "deduct",
        "linear",
        "surface_area",
        "count"
      ],
      "type": "string"
    },
    "nverts": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "perimeter_lf": {
      "description": "Length for linear/surface runs (a linear run's TOTAL incl. rise + drop), perimeter for closed ones; absent for count",
      "type": "number"
    },
    "plan_lf": {
      "description": "Linear runs with a vertical leg: the flat trace alone (#441)",
      "type": "number"
    },
    "shape_id": {
      "type": "string"
    },
    "vertical_lf": {
      "description": "Linear runs with a vertical leg: rise + drop (#441)",
      "type": "number"
    }
  },
  "required": [
    "shape_id",
    "changed",
    "measure_role",
    "nverts",
    "agent_edits"
  ],
  "type": "object"
}
sha256:f094ae7fdff80bd39debe524e3cab42fd76b73c4b7de7ecbc8613f501d649766

Description hash: sha256:0e88d60620ff788fe6c6bd62c2871ace1457e0396998e20d5273b04aa6170f64

Interface hash: sha256:d252f3ca79388b741a5e430e89eea360f5f8d00e12acd87782c1d96256e2420e

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/edit_shape",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "edit_shape"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:ed11c6e3770f3ba256d7a8d97fb0f9b64ee45839cf388dbb692bf7c5d79d0f93"
}
toolunknown0.9.990.9.100
estimate_summarykentucky-ai-opentakeoff:tool:estimate_summary
Observed interface and hashes

The priced estimate — the canvas Estimate panel as data: one line per quantity kind each measured condition carries — its area, LF and EA are separate lines (unit, order and measured quantities, rates, material / labor / supply cost, main marks each condition's first line; status priced | partial | unpriced with what is missing, or optional — a bordered linear run's derived line nobody priced, carried in its main line and never missing; set_pricing prices any line: the main one by default, the others with line "LF" / "EA" / "SF"), then material, labor, sales tax, cost, overhead, profit and the base bid. complete is false while anything is unentered: the total then counts the missing pieces at $0 and is "priced so far", and unpriced lists every hole — report it to the estimator, never fill it. Read-only.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {},
  "type": "object"
}
sha256:73fc3af6ba54a1293c44f954cf944c40d069a764ef7974e6fc74addd4231b225

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "complete": {
      "type": "boolean"
    },
    "cost": {
      "description": "material + labor + tax",
      "type": "number"
    },
    "labor": {
      "type": "number"
    },
    "lines": {
      "items": {
        "additionalProperties": {},
        "properties": {
          "finish_tag": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "key": {
            "description": "\"<condition id>:<unit>\" — one line per quantity kind the condition carries",
            "type": "string"
          },
          "labor_cost": {
            "type": "number"
          },
          "labor_qty": {
            "description": "Measured quantity in the unit — no waste",
            "type": "number"
          },
          "labor_rate": {
            "description": "$ per unit; null = never entered",
            "type": [
              "number",
              "null"
            ]
          },
          "main": {
            "description": "The condition's first line: priced by pricing.unit / material / labor and carrying its assembly items; the others price from pricing.by_unit[unit]",
            "type": "boolean"
          },
          "material_cost": {
            "type": "number"
          },
          "material_qty": {
            "description": "Order quantity in the unit — waste applied (EA never carries waste)",
            "type": "number"
          },
          "material_rate": {
            "description": "$ per unit; null = never entered",
            "type": [
              "number",
              "null"
            ]
          },
          "materials": {
            "items": {
              "additionalProperties": {},
              "properties": {
                "cost": {
                  "type": "number"
                },
                "name": {
                  "type": "string"
                },
                "price": {
                  "type": [
                    "number",
                    "null"
                  ]
                },
                "priced": {
                  "type": "boolean"
                },
                "qty": {
                  "type": "number"
                },
                "unit": {
                  "type": "string"
                }
              },
              "required": [
                "name",
                "unit",
                "qty",
                "price",
                "cost",
                "priced"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "materials_cost": {
            "type": "number"
          },
          "missing": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "optional": {
            "description": "A bordered linear run's derived line: priceable, but an empty rate is carried in the main line, never missing",
            "type": "boolean"
          },
          "status": {
            "description": "optional = an optional line nobody priced (not in unpriced)",
            "enum": [
              "priced",
              "partial",
              "unpriced",
              "optional"
            ],
            "type": "string"
          },
          "total": {
            "type": "number"
          },
          "unit": {
            "enum": [
              "SF",
              "SY",
              "LF",
              "EA"
            ],
            "type": "string"
          }
        },
        "required": [
          "id",
          "finish_tag",
          "unit",
          "material_qty",
          "labor_qty",
          "material_rate",
          "labor_rate",
          "material_cost",
          "labor_cost",
          "materials",
          "materials_cost",
          "total",
          "status",
          "missing"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "material": {
      "description": "Condition material + supply rows",
      "type": "number"
    },
    "note": {
      "type": "string"
    },
    "overhead": {
      "type": "number"
    },
    "profit": {
      "type": "number"
    },
    "settings": {
      "additionalProperties": {},
      "properties": {
        "overhead_pct": {
          "type": "number"
        },
        "profit_mode": {
          "enum": [
            "markup",
            "margin"
          ],
          "type": "string"
        },
        "profit_pct": {
          "type": "number"
        },
        "tax_pct": {
          "type": "number"
        }
      },
      "required": [
        "tax_pct",
        "overhead_pct",
        "profit_pct",
        "profit_mode"
      ],
      "type": "object"
    },
    "settings_source": {
      "type": "string"
    },
    "tax": {
      "description": "Sales tax on material",
      "type": "number"
    },
    "total": {
      "description": "The base bid — 'priced so far' while complete is false",
      "type": "number"
    },
    "unpriced": {
      "items": {
        "additionalProperties": {},
        "properties": {
          "finish_tag": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "missing": {
            "description": "What was never entered: \"material\", \"labor\", or \"material row: <name>\"",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "status": {
            "enum": [
              "partial",
              "unpriced"
            ],
            "type": "string"
          },
          "unit": {
            "description": "Which of the condition's lines is unpriced",
            "enum": [
              "SF",
              "SY",
              "LF",
              "EA"
            ],
            "type": "string"
          }
        },
        "required": [
          "id",
          "finish_tag",
          "status",
          "missing"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "warnings": {
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "settings",
    "settings_source",
    "lines",
    "material",
    "labor",
    "tax",
    "cost",
    "overhead",
    "profit",
    "total",
    "complete",
    "unpriced",
    "warnings",
    "note"
  ],
  "type": "object"
}
sha256:58b8a253ece79ad6a1418861ed5dd34bb6743cc46f9f243f9dae734eef331c4d

Description hash: sha256:ec705b058b7d01482bce331b5777c692d0580a0b2eaf20a805e2f5af53dbd1f5

Interface hash: sha256:027fca692fc81dd8df162bb9feef1f9bffab40d9bba34f5f04a87d26450ce101

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/estimate_summary",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "estimate_summary"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:a6b964973ddabe5543d0972dcbd8c4491cbe8e52acbc187a8dce14ceec831aa4"
}
toolread0.9.990.9.105
export_dxfkentucky-ai-opentakeoff:tool:export_dxf
Observed interface and hashes

The takeoff as a CAD drawing — a DXF (R2000) AutoCAD, BricsCAD, LibreCAD and Revit import as native geometry, not a picture. ONE sheet per file, like a DWG: every committed shape on that sheet becomes an LWPOLYLINE (floor rings CLOSED, walls and linear runs open, count marks a 1-ft circle), on a layer named for its finish — OT-<TAG>, with -DEDUCT / -HOLE / -WALL / -LINEAR / -COUNT suffix layers so a CAD user isolates any bucket with one layer filter, and room labels as TEXT on OT-LABELS. Coordinates are real units in the sheet's own frame: origin at the sheet's BOTTOM-left, Y up (CAD convention), feet by default ($INSUNITS 2) or metres with units:"m"; a ring's area in CAD equals its area in export_report to rounding, so the drawing IS the audit. Requires the sheet's scale (refuses otherwise — pixels in a DXF are worse than nothing); with several sheets carrying shapes, pass sheet to choose the drawing (the refusal lists them). The reply names every shape left out and why — a reconciled deduct ships as its parent's -HOLE ring, never twice. Writes to path (required — a DXF lives on disk, next to the DWG it aligns to); pair with export_marked_pdf for the reviewed planset.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "overwrite": {
      "description": "Replace the file at path even when it is not an OpenTakeoff export. Off by default: re-exporting over a previous export of your own already overwrites without this, so you only need it to deliberately destroy an unrelated file.",
      "type": "boolean"
    },
    "path": {
      "description": "File path to write the .dxf to",
      "type": "string"
    },
    "sheet": {
      "description": "Sheet key (\"plan.pdf\", \"plan.pdf#2\") or title-block number (\"A-101\"). Optional only when exactly one calibrated sheet carries shapes",
      "type": "string"
    },
    "units": {
      "description": "Output units — \"ft\" (default) or \"m\"",
      "enum": [
        "ft",
        "m"
      ],
      "type": "string"
    }
  },
  "required": [
    "path"
  ],
  "type": "object"
}
sha256:e7e19fc3645e822bc9c9a2013f115745ec679b3eecf223907ac83ce1cbe83a6d

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "bytes": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "entities": {
      "description": "LWPOLYLINE + CIRCLE + TEXT entities in model space",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "extents": {
      "anyOf": [
        {
          "additionalProperties": false,
          "properties": {
            "max": {
              "additionalItems": false,
              "items": [
                {
                  "type": "number"
                },
                {
                  "type": "number"
                }
              ],
              "maxItems": 2,
              "minItems": 2,
              "type": "array"
            },
            "min": {
              "additionalItems": false,
              "items": [
                {
                  "type": "number"
                },
                {
                  "type": "number"
                }
              ],
              "maxItems": 2,
              "minItems": 2,
              "type": "array"
            }
          },
          "required": [
            "min",
            "max"
          ],
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "description": "Model-space bounding box in output units; origin = sheet's bottom-left, Y up"
    },
    "layers": {
      "description": "Layer names in table order — OT-<TAG>, plus -DEDUCT/-HOLE/-WALL/-LINEAR/-COUNT suffix layers and OT-LABELS",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "path": {
      "description": "The DXF written",
      "type": "string"
    },
    "shapes": {
      "description": "Committed shapes that produced geometry",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "sheet": {
      "description": "Sheet key the drawing was cut from",
      "type": "string"
    },
    "sheet_number": {
      "type": [
        "string",
        "null"
      ]
    },
    "skipped": {
      "description": "Shapes on this sheet left out, each with why — never silent",
      "items": {
        "additionalProperties": false,
        "properties": {
          "id": {
            "type": "string"
          },
          "reason": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "units": {
      "enum": [
        "ft",
        "m"
      ],
      "type": "string"
    }
  },
  "required": [
    "path",
    "sheet",
    "sheet_number",
    "units",
    "layers",
    "entities",
    "shapes",
    "skipped",
    "extents",
    "bytes"
  ],
  "type": "object"
}
sha256:b85615c159f427e6cb2b17595bdfb4cca40fef1715994b1483a0e6bd337d8fab

Description hash: sha256:b23cc538d8502f8863f36efc62bdd07b86731841df4f785f8178cef58868dbb2

Interface hash: sha256:13efc09c7bd6d64287035171ea8e4bf2fce9b3de2cf3cc5ae2c9a5a816bb107b

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/export_dxf",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "export_dxf"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:956951482c068945a12f9a6ba2c0bd5933a8d4033eff82ac1675edb9df92d4c2"
}
toolunknown0.9.990.9.100
export_estimatekentucky-ai-opentakeoff:tool:export_estimate
Observed interface and hashes

Write the priced estimate as an Excel workbook — the canvas Estimate panel's Excel button: an Estimate tab (every line, then material, labor, tax, overhead, profit, base bid), a Materials tab (each supply's packages, price, cost) and, when anything is unentered, an Unpriced tab. Values only; an unentered rate is an empty cell, never 0. Every tab ends with "Prepared with OpenTakeoff". Default path: next to the loaded plan as "<project or plan> - estimate.xlsx". The reply repeats complete and unpriced — tell the user when the total is only priced so far.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "company_name": {
      "description": "Prepared-by line",
      "type": "string"
    },
    "overwrite": {
      "description": "Replace the file at path even when it is not an OpenTakeoff export. Off by default: re-exporting over a previous export of your own already overwrites without this, so you only need it to deliberately destroy an unrelated file.",
      "type": "boolean"
    },
    "path": {
      "description": "Where to write the .xlsx (default: \"<plan dir>/<project or plan> - estimate.xlsx\")",
      "type": "string"
    },
    "project_name": {
      "description": "Project name on each tab (default: the plan file's name)",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:ea6ff1f3830b649787c9a79b054e2d154471e8df06bf2282097aa6476fe9ca9c

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "complete": {
      "type": "boolean"
    },
    "path": {
      "type": "string"
    },
    "tabs": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "total": {
      "type": "number"
    },
    "unpriced": {
      "items": {
        "additionalProperties": {},
        "properties": {
          "finish_tag": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "missing": {
            "description": "What was never entered: \"material\", \"labor\", or \"material row: <name>\"",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "status": {
            "enum": [
              "partial",
              "unpriced"
            ],
            "type": "string"
          },
          "unit": {
            "description": "Which of the condition's lines is unpriced",
            "enum": [
              "SF",
              "SY",
              "LF",
              "EA"
            ],
            "type": "string"
          }
        },
        "required": [
          "id",
          "finish_tag",
          "status",
          "missing"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "path",
    "tabs",
    "total",
    "complete",
    "unpriced"
  ],
  "type": "object"
}
sha256:a4c8f146d6279cf5b0ebcea39fc41a05ca245b6ce051c89d041fe49961e8c7da

Description hash: sha256:5825d50f62cdea4de41fe2b65816d22d22ba432dbed7b795e9ad5db73fef2da8

Interface hash: sha256:2a75eb937bce1ceec195972da435a75a5e0c9412da1d8bfb7a226ad5b8d81aaf

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/export_estimate",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "export_estimate"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:9d5a897ec78463d4180f205e4cc9082782211e2abe38356f60506389aa51a493"
}
toolunknown0.9.990.9.105
export_marked_pdfkentucky-ai-opentakeoff:tool:export_marked_pdf
Observed interface and hashes

The MARKED-UP PLANSET — the deliverable of every takeoff. Writes a distribution-ready PDF to disk: a legend cover (per-condition totals, swatches, a by-sheet breakdown) followed by every sheet that carries takeoff shapes or annotations, vector-copied from the source plan with the work burned in as drawn — condition colors and hatches, a quantity chip on every shape, annotation clouds/callouts/highlights, and approval marks (the estimator's APPROVED rings, the agent's AGENT diamonds — the cover tallies the split). Built by the same module as the canvas's MARKED SET button, so agent output and app output are one implementation. Every page carries a light diagonal "OpenTakeoff" and the line "Prepared with OpenTakeoff · opentakeoff.kentucky-ai.com". A construction takeoff is no good without markup: finish EVERY takeoff by writing this file and giving the user its path (export_report carries the numbers for pricing; this carries the evidence). When the shapes were machine-traced and unreviewed, the document says so on its last page — the review path is importing the export_takeoff payload into the app, where agent shapes arrive as pencil proposals. Default path: next to the loaded plan as "<plan> - marked set.pdf". Needs no native canvas — pure vector copy, so it works even where view_sheet cannot render. The one source it refuses: an ENCRYPTED plan PDF (owner password, empty user password — it opens everywhere, but its pages cannot be vector-copied and there is no canvas here to render them); the refusal names the sheet — export the marked set from the app, or supply an unencrypted PDF.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "overwrite": {
      "description": "Replace the file at path even when it is not an OpenTakeoff export. Off by default: re-exporting over a previous export of your own already overwrites without this, so you only need it to deliberately destroy an unrelated file.",
      "type": "boolean"
    },
    "path": {
      "description": "Where to write the PDF (default: \"<plan dir>/<plan> - marked set.pdf\")",
      "type": "string"
    },
    "project_name": {
      "description": "Cover-page project name (default: the plan file's name)",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:87bf55229ef5496ecf4d66a574a3cc8f39e78d17584b96f2bc3a9d95aed2380f

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "annotations_drawn": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "approvals_drawn": {
      "description": "Approval-family glyphs burned in (#176) — estimator APPROVED rings + agent AGENT diamonds; the cover tallies the split when any exist",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "note": {
      "type": "string"
    },
    "pages": {
      "description": "Legend cover + the RFI schedule page(s) when any RFI is live + one page per marked sheet",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "path": {
      "description": "Absolute path of the written marked-set PDF — hand this to the user",
      "type": "string"
    },
    "rfis_printed": {
      "description": "Live RFIs printed on the RFI schedule page (#364) — agent-raised and panel-raised alike; withdrawn ones leave a numbering gap",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shapes_drawn": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "sheets_marked": {
      "description": "Sheets carrying shapes, annotations, or approval marks — unmarked sheets are omitted",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "path",
    "pages",
    "sheets_marked",
    "shapes_drawn",
    "annotations_drawn",
    "approvals_drawn",
    "rfis_printed",
    "note"
  ],
  "type": "object"
}
sha256:21d39887bf93dadb20b6faab24192e4a002c978bbca5be8d279b81212b9830f8

Description hash: sha256:2c7edd832fd6b349cecc23763851dfee132818705907d331943d329323a839ce

Interface hash: sha256:40d66cdf6078227fcf1e9d98a0d3d8bca3524d9fbc02003afe777e4f474bb169

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/export_marked_pdf",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "export_marked_pdf"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:a87de5bb9b897b041b57d7d9e13653e84ba6110fafbba77fac45947009be6337"
}
toolwrite0.9.990.9.100
export_proposalkentucky-ai-opentakeoff:tool:export_proposal
Observed interface and hashes

Write the bid proposal PDF — the canvas Proposal dialog's download: letterhead from company, prepared-for (set_estimate_settings client), the scope (each condition, its spec description, measured quantity), the base bid (lump sum, or itemized when the project's proposal says so), inclusions / exclusions / terms and signature blocks. Every page carries a light diagonal "OpenTakeoff" and the line "Prepared with OpenTakeoff · opentakeoff.kentucky-ai.com". Pass company exactly as the estimator gave it — this server has no Company setup of its own. It never refuses an incomplete estimate; the reply's complete and unpriced say what the base bid is missing, and the user must hear it before sending. Default path: next to the loaded plan as "<project or plan> - proposal.pdf".

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "company": {
      "description": "The contractor's letterhead, from the estimator",
      "properties": {
        "address": {
          "type": "string"
        },
        "email": {
          "type": "string"
        },
        "license": {
          "type": "string"
        },
        "name": {
          "type": "string"
        },
        "phone": {
          "type": "string"
        }
      },
      "type": "object"
    },
    "overwrite": {
      "description": "Replace the file at path even when it is not an OpenTakeoff export. Off by default: re-exporting over a previous export of your own already overwrites without this, so you only need it to deliberately destroy an unrelated file.",
      "type": "boolean"
    },
    "path": {
      "description": "Where to write the PDF (default: \"<plan dir>/<project or plan> - proposal.pdf\")",
      "type": "string"
    },
    "project_name": {
      "description": "Project name on the proposal (default: the plan file's name)",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:e1ab08392df02bac9dc74789e48e859d785edfdc769dd5c9627ba3cf1ca660a4

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "base_bid": {
      "type": "number"
    },
    "complete": {
      "type": "boolean"
    },
    "itemized": {
      "type": "boolean"
    },
    "note": {
      "type": "string"
    },
    "pages": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "path": {
      "type": "string"
    },
    "unpriced": {
      "items": {
        "additionalProperties": {},
        "properties": {
          "finish_tag": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "missing": {
            "description": "What was never entered: \"material\", \"labor\", or \"material row: <name>\"",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "status": {
            "enum": [
              "partial",
              "unpriced"
            ],
            "type": "string"
          },
          "unit": {
            "description": "Which of the condition's lines is unpriced",
            "enum": [
              "SF",
              "SY",
              "LF",
              "EA"
            ],
            "type": "string"
          }
        },
        "required": [
          "id",
          "finish_tag",
          "status",
          "missing"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "path",
    "pages",
    "base_bid",
    "itemized",
    "complete",
    "unpriced"
  ],
  "type": "object"
}
sha256:24ef2d113582c8c24d3066c245ea08833e20d9cbd72f66e8153b8f0a231dcfd5

Description hash: sha256:131183f8c139aae5d54f21444b5af5d7658d43d85ec69439bcd1f2d4dfaadcef

Interface hash: sha256:c298cbe88a383f661434bb1e15628d2860934a37cd77fb0aaf76800d9c05b894

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/export_proposal",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "export_proposal"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:3a07024e39d6e1479fecf43b38f6dcf671feb1557e6122ba8829c07c6f595c4f"
}
toolwrite0.9.990.9.105
export_reportkentucky-ai-opentakeoff:tool:export_report
Observed interface and hashes

The computed Report document — "opentakeoff.report.v1", the same schema the canvas Report's JSON export writes. Everything a pricing consumer needs without re-implementing the app's math: per-condition quantities with waste and multiplier applied (gross and *_net), the computed materials BUY LIST per condition (order quantity = basis ÷ coverage rate, rounded up to whole purchase units) plus the project-wide roll-up summed by (name, unit), per-sheet BASE subtotals, scale provenance per sheet, and annotations. Contrast: export_takeoff is the raw canvas payload (materials as CONFIG rows, no computed quantities) and takeoff_summary strips materials for a compact reply — when the numbers are leaving for pricing, consume this. A report alone is HALF the deliverable: pair it with export_marked_pdf, because a takeoff is reviewed on marked drawings, not on numbers. Returned inline; pass path to also write it to disk as JSON.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "overwrite": {
      "description": "Replace the file at path even when it is not an OpenTakeoff export. Off by default: re-exporting over a previous export of your own already overwrites without this, so you only need it to deliberately destroy an unrelated file.",
      "type": "boolean"
    },
    "path": {
      "description": "File path to write the document to",
      "type": "string"
    },
    "project_name": {
      "description": "Label for the document's project_name field (a headless session has no project of its own; omitted → null)",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:eebb520a46313fda9f852bf597fe726a3791b344a60f8d48cee32988706996ab

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "by_label": {
      "items": {
        "additionalProperties": {},
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    },
    "by_sheet": {
      "description": "BASE per-sheet subtotals — multiplier NOT applied, no waste, no materials",
      "items": {
        "additionalProperties": {},
        "properties": {
          "rows": {
            "items": {
              "additionalProperties": {},
              "propertyNames": {
                "type": "string"
              },
              "type": "object"
            },
            "type": "array"
          },
          "sheet": {
            "type": "string"
          },
          "sheet_id": {
            "type": "string"
          }
        },
        "required": [
          "sheet_id",
          "sheet",
          "rows"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "condition_columns": {
      "items": {
        "additionalProperties": {},
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    },
    "conditions": {
      "description": "conditionTotals rows: gross + *_net quantities AND the computed materials buy list",
      "items": {
        "additionalProperties": {},
        "properties": {
          "border_sf": {
            "type": "number"
          },
          "border_sf_net": {
            "type": "number"
          },
          "ea": {
            "type": "number"
          },
          "finish_tag": {
            "type": "string"
          },
          "floor_sf": {
            "type": "number"
          },
          "floor_sf_net": {
            "type": "number"
          },
          "id": {
            "type": "string"
          },
          "lf": {
            "type": "number"
          },
          "lf_net": {
            "type": "number"
          },
          "materials": {
            "items": {
              "additionalProperties": {},
              "properties": {
                "basis": {
                  "enum": [
                    "area",
                    "linear",
                    "count",
                    "seam_lf"
                  ],
                  "type": "string"
                },
                "basis_qty": {
                  "description": "The condition total this row divides (SF, LF, EA, or figured seam LF — multiplier applied, waste not)",
                  "type": "number"
                },
                "name": {
                  "type": "string"
                },
                "per": {
                  "description": "Coverage rate — basis units per purchase unit",
                  "type": "number"
                },
                "qty": {
                  "description": "Computed order quantity",
                  "type": "number"
                },
                "round": {
                  "type": "boolean"
                },
                "unit": {
                  "description": "Purchase unit, e.g. 'gal', 'bag'",
                  "type": "string"
                }
              },
              "required": [
                "name",
                "unit",
                "per",
                "basis",
                "round",
                "basis_qty",
                "qty"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "multiplier": {
            "type": "number"
          },
          "shape_count": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "sy_net": {
            "type": "number"
          },
          "total_sf": {
            "type": "number"
          },
          "total_sf_net": {
            "type": "number"
          },
          "wall_sf": {
            "type": "number"
          },
          "wall_sf_net": {
            "type": "number"
          },
          "waste_pct": {
            "type": "number"
          }
        },
        "required": [
          "id",
          "finish_tag",
          "multiplier",
          "waste_pct",
          "shape_count",
          "floor_sf",
          "wall_sf",
          "border_sf",
          "lf",
          "ea",
          "total_sf",
          "floor_sf_net",
          "wall_sf_net",
          "border_sf_net",
          "lf_net",
          "total_sf_net",
          "sy_net",
          "materials"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "display_units": {
      "type": "string"
    },
    "generated_with": {
      "type": "string"
    },
    "markups": {
      "items": {
        "additionalProperties": {},
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    },
    "materials": {
      "description": "Project-wide buy list — condition rows summed by (name, unit)",
      "items": {
        "additionalProperties": {},
        "properties": {
          "name": {
            "type": "string"
          },
          "qty": {
            "type": "number"
          },
          "unit": {
            "type": "string"
          }
        },
        "required": [
          "name",
          "unit",
          "qty"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "project_name": {
      "type": [
        "string",
        "null"
      ]
    },
    "proposed_condition_edits": {
      "description": "Pending condition-edit proposals (#365) — the rows above print the CURRENT knobs; each entry here carries the proposed values beside them. Present only when any are pending, so a proposal-free report is byte-identical",
      "items": {
        "additionalProperties": false,
        "properties": {
          "condition": {
            "type": "string"
          },
          "condition_id": {
            "type": "string"
          },
          "current": {
            "additionalProperties": {},
            "description": "The condition's knobs as they stand — what every total above is computed from",
            "properties": {
              "drop_ft": {
                "type": "number"
              },
              "finish_tag": {
                "type": "string"
              },
              "height_ft": {
                "type": "number"
              },
              "multiplier": {
                "type": "number"
              },
              "rise_ft": {
                "type": "number"
              },
              "roll_setup": {
                "anyOf": [
                  {
                    "additionalProperties": {},
                    "properties": {},
                    "type": "object"
                  },
                  {
                    "type": "null"
                  }
                ]
              },
              "waste_pct": {
                "type": "number"
              }
            },
            "type": "object"
          },
          "proposal_id": {
            "type": "string"
          },
          "proposed": {
            "additionalProperties": {},
            "description": "Only the fields that would change",
            "properties": {
              "drop_ft": {
                "type": "number"
              },
              "finish_tag": {
                "type": "string"
              },
              "height_ft": {
                "type": "number"
              },
              "multiplier": {
                "type": "number"
              },
              "rise_ft": {
                "type": "number"
              },
              "roll_setup": {
                "anyOf": [
                  {
                    "additionalProperties": {},
                    "properties": {},
                    "type": "object"
                  },
                  {
                    "type": "null"
                  }
                ]
              },
              "waste_pct": {
                "type": "number"
              }
            },
            "type": "object"
          },
          "proposed_at": {
            "type": "string"
          },
          "rationale": {
            "type": "string"
          }
        },
        "required": [
          "proposal_id",
          "condition",
          "condition_id",
          "current",
          "proposed",
          "rationale",
          "proposed_at"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "rfis": {
      "items": {
        "additionalProperties": {},
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    },
    "roll_goods": {
      "description": "Roll-goods order rows (#136) — order_lf / rolls / order_qty per roll-goods condition, ×N applied; empty when no condition carries a roll_setup (always the case for a headless session today)",
      "items": {
        "additionalProperties": {},
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    },
    "schema": {
      "const": "opentakeoff.report.v1",
      "type": "string"
    },
    "shape_labels": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "sheets": {
      "description": "Scale provenance per sheet — how each scale was set",
      "items": {
        "additionalProperties": {},
        "properties": {
          "scale_source": {
            "type": "string"
          },
          "sheet": {
            "type": "string"
          },
          "sheet_id": {
            "type": "string"
          }
        },
        "required": [
          "sheet_id",
          "sheet",
          "scale_source"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "totals": {
      "additionalProperties": {},
      "properties": {
        "ea": {
          "type": "number"
        },
        "lf": {
          "type": "number"
        },
        "lf_net": {
          "type": "number"
        },
        "sy_net": {
          "type": "number"
        },
        "total_sf": {
          "type": "number"
        },
        "total_sf_net": {
          "type": "number"
        }
      },
      "required": [
        "total_sf",
        "total_sf_net",
        "lf",
        "lf_net",
        "ea",
        "sy_net"
      ],
      "type": "object"
    },
    "units": {
      "type": "string"
    }
  },
  "required": [
    "schema",
    "project_name",
    "generated_with",
    "sheets",
    "conditions",
    "by_sheet",
    "totals",
    "materials",
    "markups",
    "rfis",
    "condition_columns",
    "shape_labels",
    "by_label",
    "units",
    "display_units",
    "roll_goods"
  ],
  "type": "object"
}
sha256:ac1f3255225d734e591ed7ade1daa6c038ea3fe453bbfa4be465068dd9c66d29

Description hash: sha256:43a9ce02fb6a1131ec784acee8eb833833c707fc2fffe3b294bab3b7a1c09e06

Interface hash: sha256:5de21a1bf03ce48f5ffa87fbc9554a3b59cb92cd9cea02b4d6e9f252dd157f98

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/export_report",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "export_report"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:4530c232116cd30e4391d59e526ffd529b71757e3d4365f10107c2022703590a"
}
toolunknown0.9.990.9.100
export_takeoffkentucky-ai-opentakeoff:tool:export_takeoff
Observed interface and hashes

The full "opentakeoff.takeoff_canvas.v1" annotations payload — exactly what the app autosaves, importable by it. Returned inline; pass path to also write it to disk as JSON. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "overwrite": {
      "description": "Replace the file at path even when it is not an OpenTakeoff export. Off by default: re-exporting over a previous export of your own already overwrites without this, so you only need it to deliberately destroy an unrelated file.",
      "type": "boolean"
    },
    "path": {
      "description": "File path to write the payload to",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:41e41096ddc7d69307542f3ee77dfec685906bfe1c543fda3bed7a6b96f77e7e

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "approvals": {
      "description": "Approval-family records (#176) — the estimator's APPROVED seals and the agent's verdict marks {id, actor, ts, sheet_id, at:[nx,ny], shape_id?, text?}. Present only when any exist (the canvas payload's own convention), so a verdict-free export stays byte-identical",
      "items": {},
      "type": "array"
    },
    "bid_proposal": {
      "additionalProperties": {},
      "description": "The project's proposal layout and text — present once set",
      "properties": {},
      "type": "object"
    },
    "client_info": {
      "additionalProperties": {},
      "description": "Who the proposal is for (client_name, client_address, reference) — present once set_estimate_settings or an import set it",
      "properties": {},
      "type": "object"
    },
    "condition_edit_proposals": {
      "description": "Pending condition-edit diffs (#365) — present only when any exist. Nothing on the condition changes until the estimator accepts in the canvas",
      "items": {
        "additionalProperties": {},
        "properties": {
          "condition_id": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "proposed": {
            "additionalProperties": {},
            "properties": {},
            "type": "object"
          },
          "proposed_at": {
            "type": "string"
          },
          "rationale": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "condition_id",
          "proposed",
          "rationale",
          "proposed_at"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "conditions": {
      "items": {
        "additionalProperties": {},
        "properties": {
          "color": {
            "type": "string"
          },
          "fill": {
            "type": "string"
          },
          "finish_tag": {
            "type": "string"
          },
          "hatch": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "materials": {
            "items": {},
            "type": "array"
          },
          "multiplier": {
            "type": "number"
          },
          "waste_pct": {
            "type": "number"
          }
        },
        "required": [
          "id",
          "finish_tag",
          "color",
          "fill",
          "hatch",
          "multiplier",
          "waste_pct",
          "materials"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "estimate_settings": {
      "additionalProperties": {},
      "description": "The project's markups (tax_pct, overhead_pct, profit_pct, profit_mode) — present once set",
      "properties": {},
      "type": "object"
    },
    "last_group": {
      "items": {},
      "type": "array"
    },
    "markups": {
      "items": {},
      "type": "array"
    },
    "project_name": {
      "type": "string"
    },
    "proposals": {
      "description": "Proposal batches (#365) — present only when any exist. Shapes reference them by origin.proposal_id; the canvas shows one Accept per batch",
      "items": {
        "additionalProperties": {},
        "properties": {
          "created_at": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "label": {
            "type": "string"
          },
          "rationale": {
            "type": "string"
          },
          "withdrawn_at": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "label",
          "rationale",
          "created_at"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "rfis": {
      "description": "Live RFI records; withdrawn tombstones are omitted",
      "items": {},
      "type": "array"
    },
    "schema": {
      "type": "string"
    },
    "shapes": {
      "items": {
        "additionalProperties": {},
        "properties": {
          "computed": {
            "additionalProperties": {},
            "description": "count shapes carry {count} alone; every other role carries area_sf + perimeter_lf",
            "properties": {
              "area_sf": {
                "type": "number"
              },
              "count": {
                "type": "number"
              },
              "perimeter_lf": {
                "type": "number"
              }
            },
            "type": "object"
          },
          "condition_id": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "measure_role": {
            "enum": [
              "floor_area",
              "deduct",
              "linear",
              "surface_area",
              "count"
            ],
            "type": "string"
          },
          "origin": {
            "additionalProperties": {},
            "description": "Provenance: method (manual|one_click_v1), actor (omitted=human, 'agent'=MCP/automation), reviewed (human affirmed at an explicit gate), assignment (where the finish tag came from — {source: 'schedule', room_tag, surface, schedule_sheet} when the room's own schedule row decided it, {source: 'asserted'} when the agent chose; stamped on every agent commit), and correction fields (edited, edited_before_create, copied, proposed_verts_norm, edits)",
            "properties": {},
            "type": "object"
          },
          "sheet_id": {
            "type": "string"
          },
          "verts_norm": {
            "description": "Vertices normalized to sheet dims (0–1)",
            "items": {
              "additionalItems": false,
              "items": [
                {
                  "type": "number"
                },
                {
                  "type": "number"
                }
              ],
              "maxItems": 2,
              "minItems": 2,
              "type": "array"
            },
            "type": "array"
          }
        },
        "required": [
          "id",
          "sheet_id",
          "condition_id",
          "measure_role",
          "verts_norm",
          "computed"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "sheet_group": {
      "items": {},
      "type": "array"
    },
    "sheet_levels": {
      "additionalProperties": {},
      "description": "Present only when a sheet carries a level label (the app omits it when empty)",
      "properties": {},
      "type": "object"
    },
    "sheet_tabs": {
      "items": {},
      "type": "array"
    },
    "sheets": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "scale_confirmed": {
            "description": "False for agent-set calibration until a human confirms it",
            "type": "boolean"
          },
          "scale_source": {
            "description": "How the exported calibration was established",
            "type": "string"
          },
          "sheet_id": {
            "type": "string"
          },
          "units_per_px": {
            "type": "number"
          }
        },
        "required": [
          "sheet_id",
          "units_per_px"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "units": {
      "description": "Present only for a metric project; absent means imperial — the app's own diff-only convention",
      "type": "string"
    }
  },
  "required": [
    "schema",
    "project_name",
    "sheets",
    "conditions",
    "shapes",
    "markups",
    "sheet_group",
    "last_group",
    "sheet_tabs"
  ],
  "type": "object"
}
sha256:d20888f46d35f1f78f284bc967c15394c21f95231157a832c79c27bb8d63827e

Description hash: sha256:f6168700902ba539612319577c773ee630deea1525472fda94b6d9350566d211

Interface hash: sha256:67c2137a8e3e3c25618b3592184ec09c354e6fac92dd0a241f1dcea4338ebbda

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/export_takeoff",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "export_takeoff"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:75b40131436b3e71545e49596354ff983ff26fc43d28f1307e74ff6b20904c36"
}
toolunknown0.9.990.9.100
find_schedulekentucky-ai-opentakeoff:tool:find_schedule
Observed interface and hashes

Locate a schedule table in the set (#87): pass a kind ("room finish", "material"/"finish") and get every matching table's sheet, title, headers, TOTAL row count, and REGION — sized for a view_sheet look or a read_sheet_text pull of exactly the table. A schedule continued across sheets is ONE match whose "parts" list every fragment (base first) with its own viewable region; tables read through rotated headers say so; a table answering for one building carries "building"; a table with delta/REV-marked rows says how many in "revised_rows". Errors with what WAS found when the asked-for kind isn't in the set. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "kind": {
      "description": "\"room finish\" (rooms → surface finishes), \"finish\"/\"material\" (codes → products), or \"equipment\" (MEP device schedules — fans, pumps, heaters, AHUs, VAVs, diffusers/grilles/registers — keyed by mark, proven by a powered or air-device column)",
      "type": "string"
    }
  },
  "required": [
    "kind"
  ],
  "type": "object"
}
sha256:ee13122a7275bd23e5a61e37ec25def76088770fe21c82ee01999488142807b1

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "matches": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "building": {
            "description": "The building this table answers for, when its title or sheet names one",
            "type": "string"
          },
          "headers": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "kind": {
            "type": "string"
          },
          "parts": {
            "description": "Present when the table CONTINUES across sheets ('… SCHEDULE — CONT'D'): every fragment, base first, each with its own viewable region",
            "items": {
              "additionalProperties": false,
              "properties": {
                "region": {
                  "additionalProperties": false,
                  "properties": {
                    "x0": {
                      "type": "number"
                    },
                    "x1": {
                      "type": "number"
                    },
                    "y0": {
                      "type": "number"
                    },
                    "y1": {
                      "type": "number"
                    }
                  },
                  "required": [
                    "x0",
                    "y0",
                    "x1",
                    "y1"
                  ],
                  "type": "object"
                },
                "rows": {
                  "maximum": 9007199254740991,
                  "minimum": -9007199254740991,
                  "type": "integer"
                },
                "sheet": {
                  "type": "string"
                },
                "title": {
                  "type": "string"
                }
              },
              "required": [
                "sheet",
                "title",
                "rows",
                "region"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "region": {
            "additionalProperties": false,
            "description": "Pass to view_sheet to look at the table (the BASE fragment's region when the table continues)",
            "properties": {
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "revised_rows": {
            "description": "Rows carrying a delta/REV marker — the ink changed there; resolve those tags to see which",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "rotated_headers": {
            "description": "true when the column headers were read at a quarter-turn",
            "type": "boolean"
          },
          "rows": {
            "description": "Total data rows — a continued schedule counts every fragment's rows",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "sheet": {
            "type": "string"
          },
          "title": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "kind",
          "title",
          "rows",
          "headers",
          "region"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "matches"
  ],
  "type": "object"
}
sha256:619b378953e7288d10bd9edccc9077276aee1309172791a9310f5042e9e8bd53

Description hash: sha256:20ec5897526bbbf2c192838b0fadfbd669e6bad4417fb25a6ac8baabc1556e86

Interface hash: sha256:746d74f8ccd2f52123edff97bba421a08fc7baacaf8958f60a14caf6b52317b1

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/find_schedule",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "find_schedule"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:fdc9f64ad6167ede622ed3ea0addbe3da2e0cf557e71fb6091b88adf573c4d30"
}
toolunknown0.9.990.9.100
find_textkentucky-ai-opentakeoff:tool:find_text
Observed interface and hashes

LOCATE a known string on a sheet — the complement to read_sheet_text (which returns what a region SAYS; this finds WHERE a string you already know sits). Case-insensitive substring match against each pdf.js text run, so a room label split across runs ("OFFICE" then "134" as separate items) needs a find_text call per fragment, or read_sheet_text over a region to see the whole thing joined. Every hit tells you which room a polygon belongs to — the locate-then-trace workflow: find_text the room number, then measure_polygon (One-Click is temporarily gated on this server) on that room's wall faces. Optionally restrict to a region {x0, y0, x1, y1}; results cap at limit (default 200), with count/truncated telling you exactly how much a tighter region or higher limit would recover. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "default": 200,
      "description": "Max hits returned",
      "maximum": 2000,
      "minimum": 1,
      "type": "integer"
    },
    "q": {
      "description": "Text to find — a room number ('134'), a label fragment ('RECEPTION'), a schedule tag ('CPT-1')",
      "minLength": 1,
      "type": "string"
    },
    "region": {
      "description": "Rect in image px (origin top-left, y down); omit for the full sheet",
      "properties": {
        "x0": {
          "type": "number"
        },
        "x1": {
          "type": "number"
        },
        "y0": {
          "type": "number"
        },
        "y1": {
          "type": "number"
        }
      },
      "required": [
        "x0",
        "y0",
        "x1",
        "y1"
      ],
      "type": "object"
    },
    "sheet": {
      "type": "string"
    }
  },
  "required": [
    "sheet",
    "q"
  ],
  "type": "object"
}
sha256:36cf04ac67186b08510b81f5b53cee85d053a5b65885605688428013a023e1bf

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "count": {
      "description": "Total matches before the limit cap",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "hits": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "bbox": {
            "additionalItems": false,
            "description": "[x0, y0, x1, y1] image px",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              },
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 4,
            "minItems": 4,
            "type": "array"
          },
          "center": {
            "additionalItems": false,
            "description": "Bbox center, image px — feed straight into one_click's seed",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "str": {
            "description": "The matched pdf.js text run, verbatim (may be shorter than the full label — runs aren't merged into lines)",
            "type": "string"
          }
        },
        "required": [
          "str",
          "bbox",
          "center"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "q": {
      "type": "string"
    },
    "sheet": {
      "type": "string"
    },
    "truncated": {
      "description": "true = count exceeds hits.length; narrow the region or raise limit",
      "type": "boolean"
    }
  },
  "required": [
    "sheet",
    "q",
    "count",
    "truncated",
    "hits"
  ],
  "type": "object"
}
sha256:8d8304c4c4c59dd9cd62f8b17c43a86239b8f734e02ce635190f2d6b13f0a1ae

Description hash: sha256:8195ca41eb48f1db7ad9fc7206b8d2171e0159dcdfbfeb2f4b230160dd2b0732

Interface hash: sha256:200ac539d8f23ef901948d65abb3900b0acc473906d0ff48dd4ca4d430c8b93b

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/find_text",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "find_text"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:b6acea6352cf805ba97528ef5c45527ecf8b9e3dcb52e82b026aadb39a0e094c"
}
toolread0.9.990.9.100
get_sheet_vectorskentucky-ai-opentakeoff:tool:get_sheet_vectors
Observed interface and hashes

The STROKES — the sheet's vector layer exactly as the engine is fed it, so you can run your own geometry against what the app sees (#367). view_sheet lets you look, read_sheet_text lets you read, sheet_context classifies a region; this returns the raw extractor output that all of them and every shape verb (the wall network's pen weights, symbol_sweep's matching) work from: flat points [x1, y1, x2, y2, …] in image px, one meta byte per segment (low nibble flags: 1 curve chord, 2 clip-only, 4 fill-only, 8 polyline arc; pen width = meta >> 4), per-segment stroke luminance, the drawn figure each segment belongs to (subpath ordinal), the sheet's placed-image area, and its PDF layer table with a per-segment layer index (sheet_info.layers names and classifies the same ids). Nothing is classified, decimated, or merged here — segments arrive whole, in extraction order, undecimated, which is the point: a reader can build its own room finder, symbol matcher, or wall classifier on the same array and commit through the existing verbs with provenance intact. Paged, never clipped silently: a dense sheet runs to hundreds of thousands of segments, so the reply carries limit (default 20000 segments, ceiling 100000) and the ledger offset + returned + dropped === total on every page; dropped is exactly what passing next_cursor as cursor recovers. region keeps every segment that intersects the rect (endpoints untouched — the same keep test sheet_context uses, so total here equals sheet_context's total_in_region) and echoes it post-clamp. Read-only and stateless — no shape, condition, or scale is touched. A scan has no strokes: the verb refuses and names view_sheet as the path. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "cursor": {
      "description": "A previous reply's next_cursor — resume paging there. Omit for the first page",
      "maximum": 9007199254740991,
      "minimum": 0,
      "type": "integer"
    },
    "limit": {
      "default": 20000,
      "description": "Page size in segments (default 20000, max 100000) — about 1 MB of JSON per 20000",
      "maximum": 100000,
      "minimum": 1,
      "type": "integer"
    },
    "region": {
      "description": "Rect in image px (origin top-left, y down); omit for the full sheet. A segment is kept when it intersects the rect",
      "properties": {
        "x0": {
          "type": "number"
        },
        "x1": {
          "type": "number"
        },
        "y0": {
          "type": "number"
        },
        "y1": {
          "type": "number"
        }
      },
      "required": [
        "x0",
        "y0",
        "x1",
        "y1"
      ],
      "type": "object"
    },
    "sheet": {
      "description": "Sheet key (\"plan.pdf\", \"plan.pdf#2\") or title-block number (\"A-101\")",
      "type": "string"
    }
  },
  "required": [
    "sheet"
  ],
  "type": "object"
}
sha256:35d1b91dafe47b305d8ddad684e0112c319719468d018b9b9723f9634f9542bd

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "dropped": {
      "description": "Matching segments AFTER this page that limit cut — exactly what next_cursor recovers. offset + returned + dropped === total on every reply; 0 means this page ends the set",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "image_area": {
      "description": "Total placed-image area on the sheet, image px² — a value near the sheet area means a scan or photo underlay sits under whatever linework there is",
      "type": "number"
    },
    "layer_ids": {
      "description": "The sheet's PDF Optional Content Group ids in first-seen order — the same ids sheet_info.layers reports (with names and roles); [] on an unlayered sheet",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "layer_of": {
      "description": "Aligned with points: index into layer_ids, or −1 for a segment outside every layer. Empty only when the geometry carries no layer channel",
      "items": {
        "maximum": 9007199254740991,
        "minimum": -9007199254740991,
        "type": "integer"
      },
      "type": "array"
    },
    "limit": {
      "description": "The page size that applied",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "lum": {
      "description": "Aligned with points: stroke luminance 0 (black) – 255 (white), Rec. 709 over the stroke colour in force when the path was built. Empty only when the geometry carries no luminance channel",
      "items": {
        "maximum": 9007199254740991,
        "minimum": -9007199254740991,
        "type": "integer"
      },
      "type": "array"
    },
    "meta": {
      "description": "One byte per segment, aligned with points: low nibble flags — 1 curve chord (bezier tessellation or detected polyline arc), 2 clip-only path (invisible ink), 4 filled-not-stroked, 8 polyline-arc provenance; high nibble (meta >> 4) = device pen width in px",
      "items": {
        "maximum": 9007199254740991,
        "minimum": -9007199254740991,
        "type": "integer"
      },
      "type": "array"
    },
    "next_cursor": {
      "description": "Pass as cursor to fetch the next page; absent when dropped is 0",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "note": {
      "description": "Present when the sheet is a scan wrapper — the few segments here are a frame, not the drawing",
      "type": "string"
    },
    "offset": {
      "description": "Matching segments BEFORE this page (skipped by cursor)",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "page": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "points": {
      "description": "Flat [x1, y1, x2, y2, …] — four numbers per segment, image px to 0.01, endpoints exactly as extracted (never clipped to the region, never merged); segments arrive in extraction order, the order the engine sees",
      "items": {
        "type": "number"
      },
      "type": "array"
    },
    "region": {
      "description": "The region actually resolved, post-clamp [x0, y0, x1, y1] image px — the same rect sheet_context and view_sheet take, so all three verbs answer in one frame",
      "items": {
        "type": "number"
      },
      "maxItems": 4,
      "minItems": 4,
      "type": "array"
    },
    "returned": {
      "description": "Segments in this reply",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "sheet": {
      "type": "string"
    },
    "sheet_px": {
      "items": {
        "type": "number"
      },
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "subpath": {
      "description": "Aligned with points: ordinal of the drawn FIGURE each segment belongs to (each moveTo starts one, each rectangle is one) — segments sharing a value are one path; −1 = outside every figure",
      "items": {
        "maximum": 9007199254740991,
        "minimum": -9007199254740991,
        "type": "integer"
      },
      "type": "array"
    },
    "total": {
      "description": "Segments on the sheet intersecting the region — the whole set, before paging",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "sheet",
    "page",
    "sheet_px",
    "region",
    "points",
    "meta",
    "lum",
    "subpath",
    "image_area",
    "layer_ids",
    "layer_of",
    "total",
    "offset",
    "returned",
    "dropped",
    "limit"
  ],
  "type": "object"
}
sha256:644063b06c4ce688fc50e3054f4001a82803ad1309de5adf5c14fee2209098ec

Description hash: sha256:1ab5245b838ad3aeae7f9bed0581cc3587740814f6300048bab634316e20071b

Interface hash: sha256:eb256d9f25641c3fc1775b30390c0e011f7e609db20b8b1422ff1b78decae5ff

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/get_sheet_vectors",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "get_sheet_vectors"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:30e6ca724de60e3ea47b246705e7fe0ba8d891ba3c712605bd7a9dd666946ef2"
}
toolread0.9.990.9.100
import_takeoffkentucky-ai-opentakeoff:tool:import_takeoff
Observed interface and hashes

The way BACK IN (#151): load an "opentakeoff.takeoff_canvas.v1" file — a prior export_takeoff, or the app's own save — into this session, through the SAME tested merge rules as the app's Sheet-menu import: finish-tag identity joins imported conditions onto this session's own (their knobs win), new ids append, duplicate ids skip (re-import is idempotent), and THIS session's calibration wins per sheet. An uncalibrated empty session adopts the file wholesale. New dimensional shapes refuse atomically if their source scale differs from the session calibration or is missing; align scales and re-export, or use a fresh session. Counts and duplicate IDs are exempt. Legacy agent traces without review flags arrive reviewed:false. Resume yesterday's work, extend a takeoff a human already reviewed (their ink stays ink — reviewed shapes arrive untouchable by agent verbs), or audit someone else's export with list_shapes/takeoff_summary. Requires a loaded plan; shapes referencing OTHER files ride along and count in totals but can't be viewed against this document — the reply's unknown_files names them. Approval marks ride the file too — transport, not minting: an estimator seal arriving by import stays estimator ink, listable but untouchable here. undo_last removes the imported SHAPES as one step; adopted conditions, scales, annotations, and approval marks stay.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "path": {
      "description": "Path to a takeoff_canvas.v1 JSON file on disk",
      "type": "string"
    }
  },
  "required": [
    "path"
  ],
  "type": "object"
}
sha256:e95cbac795504451ebb09bcbd9099f67c40fb550adf2f85fa8592e3a3e4e6ac4

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "conditions_added": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "conditions_merged": {
      "description": "Imported conditions that joined an existing finish tag (its knobs won)",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "file": {
      "description": "Basename of the imported file",
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "replaced": {
      "description": "true = the session was empty and adopted the file wholesale",
      "type": "boolean"
    },
    "rules_imported": {
      "description": "Correction rules (#88) that arrived with the file — apply_rules re-runs them",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "scales_adopted": {
      "description": "Sheets whose calibration came from the file (this session's own always wins)",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shapes_added": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shapes_pending": {
      "description": "Of the added shapes, how many are unreviewed machine pencil",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shapes_total": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "unknown_files": {
      "description": "Files referenced by imported shapes that this document doesn't have — they count in totals but can't be viewed here",
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "file",
    "replaced",
    "shapes_added",
    "shapes_pending",
    "conditions_merged",
    "conditions_added",
    "scales_adopted",
    "unknown_files",
    "rules_imported",
    "shapes_total",
    "note"
  ],
  "type": "object"
}
sha256:16b2f6588546bc52ae9c52a9e535859f491d37490ca83cfd3e278f855d99c4be

Description hash: sha256:082869109bcbaa0b02a9a4cbbf0f40c2ec7e863656fca3def5843ca33afb56f4

Interface hash: sha256:e9591e2bee2a8bda4fd59932f6f6cc22464801f1a49408a32afeb344c22a34d0

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/import_takeoff",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "import_takeoff"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:6e9186d34d2d1b4d6442347df5676b04d9f00f7808433695bf92ed639495230c"
}
toolwrite0.9.990.9.100
link_annotationkentucky-ai-opentakeoff:tool:link_annotation
Observed interface and hashes

Attach an existing annotation to a condition, or detach it by passing an empty condition — the canvas's Attach/Detach control, reachable by an agent. Use it to tie up notes left unattached (list_annotations reports how many), or to move one to the finish it actually concerns. Attaching mints the tag on first use.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "annotation_id": {
      "description": "Id from annotate or list_annotations",
      "type": "string"
    },
    "condition": {
      "description": "Finish tag to attach to; empty string detaches",
      "type": "string"
    }
  },
  "required": [
    "annotation_id",
    "condition"
  ],
  "type": "object"
}
sha256:895cf3284350e3ae5ee7c43c9a72a9302063e809d516c8f66d993e51964b76b7

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "condition": {
      "type": "string"
    },
    "condition_id": {
      "type": "string"
    },
    "id": {
      "type": "string"
    },
    "note": {
      "type": "string"
    }
  },
  "required": [
    "id",
    "condition",
    "note"
  ],
  "type": "object"
}
sha256:c8bcaf516b9997efe9801975695d6e9c1ffda9110eeb9b2eceacf0a176afb6c6

Description hash: sha256:95e4e2b7cc4dbb050e3f0d42209e800d89e4989a71d7d772897ede4c6aa18ff7

Interface hash: sha256:02ba28d333e255b75fb5c573fbd5d1de8d4405989d285d8f38ed5fd3b9c66a32

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/link_annotation",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "link_annotation"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:310b28f20b92a89d812d2b857bf6f905552a1f4aae57e05dda3052bbe6b3a17b"
}
toolunknown0.9.990.9.100
list_annotationskentucky-ai-opentakeoff:tool:list_annotations
Observed interface and hashes

Every annotation on the takeoff, with condition_id RESOLVED to its finish tag so you can act on the reply without joining against conditions[]. Filter by sheet, by condition, or both. Coordinates come back in image px (the same frame you passed in), not the normalized form they're stored as. `unattached` counts the notes carrying no condition — the candidates for link_annotation. `verdicts` is the approval family's inventory (mark_verdict/delete_verdict): every mark with its actor stated — the estimator's APPROVED ring or the agent's AGENT diamond — under the same filters, a condition filter reaching a verdict through its target shape. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Only annotations attached to this finish tag",
      "type": "string"
    },
    "sheet": {
      "description": "Only annotations on this sheet",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:65525a9985691d5cd39e7f6791fb481a476a2f46c5f2676eae77b2159365ebfa

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "annotations": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "at": {
            "additionalItems": false,
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "condition": {
            "description": "Resolved finish tag, or '' when unattached — saves joining against conditions[]",
            "type": "string"
          },
          "condition_id": {
            "type": "string"
          },
          "from": {
            "additionalItems": false,
            "description": "Arrow tail / dimension start (image px)",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "id": {
            "type": "string"
          },
          "length_lf": {
            "description": "Dimension only: the measured length in real feet, snapshotted at annotate time from the sheet scale",
            "type": "number"
          },
          "r": {
            "description": "Bubble radius (image px)",
            "type": "number"
          },
          "rect": {
            "items": {
              "additionalItems": false,
              "items": [
                {
                  "type": "number"
                },
                {
                  "type": "number"
                }
              ],
              "maxItems": 2,
              "minItems": 2,
              "type": "array"
            },
            "type": "array"
          },
          "sheet": {
            "type": "string"
          },
          "target": {
            "additionalItems": false,
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "text": {
            "type": "string"
          },
          "text_resolved": {
            "description": "Only when text carries a {{qty}} field: the note as the sheet shows it, {{qty}} filled with the linked condition's measured quantity (multiplier applied, no waste)",
            "type": "string"
          },
          "to": {
            "additionalItems": false,
            "description": "Arrow head / dimension end (image px)",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "type": {
            "type": "string"
          },
          "unresolved_fields": {
            "description": "Fields that could not fill (no linked condition, nothing measured yet, or an unknown name) — they stay literal and print in the warning ink; link_annotation fixes the first case",
            "items": {
              "type": "string"
            },
            "type": "array"
          }
        },
        "required": [
          "id",
          "sheet",
          "type",
          "text",
          "condition",
          "condition_id"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "count": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "unattached": {
      "description": "How many carry no condition — candidates for link_annotation",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "verdict_count": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "verdicts": {
      "description": "Approval-family records (#176) under the same filters: sheet applies directly; a condition filter reaches a verdict THROUGH its target shape (a sheet-point mark carries no scope and drops out)",
      "items": {
        "additionalProperties": false,
        "properties": {
          "actor": {
            "description": "\"estimator\" = the human APPROVED ring (ink — import-borne here, never minted over MCP), \"agent\" = the AGENT diamond",
            "enum": [
              "estimator",
              "agent"
            ],
            "type": "string"
          },
          "at": {
            "additionalItems": false,
            "description": "Render anchor (image px) — absent only when the record rides a sheet from a file this session hasn't loaded (#152)",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "condition": {
            "description": "The targeted shape's finish tag, resolved — '' for sheet-point marks",
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "shape_id": {
            "description": "Present when the verdict targets a committed shape — WHAT was marked, not where it draws",
            "type": "string"
          },
          "sheet": {
            "type": "string"
          },
          "text": {
            "description": "The optional short note riding the record",
            "type": "string"
          },
          "ts": {
            "description": "ISO-8601 mint time",
            "type": "string"
          }
        },
        "required": [
          "id",
          "actor",
          "sheet",
          "condition"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "annotations",
    "count",
    "unattached",
    "verdicts",
    "verdict_count"
  ],
  "type": "object"
}
sha256:ce8c3f8d9a67e742fad6a663d5e59ac9dfbae9d372955e42fe65c9fa78adbf24

Description hash: sha256:41c08e4149e26aef477b6c08549ce80effeb005ea2c60a738b35b92d07ddcb86

Interface hash: sha256:c39374ceaf161268d1ec161666b7a14f43cc9bc4edf7432aac433fb69633ee0b

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/list_annotations",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "list_annotations"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:8d35cf4e175fb3c18dc33e3bdf79f9edc19291bdafb68d2c4b0cf8dbd97729a4"
}
toolunknown0.9.990.9.100
list_rfiskentucky-ai-opentakeoff:tool:list_rfis
Observed interface and hashes

Every RFI in the register with its status, sheet, who raised it (actor) and whether an agent-raised one is still pending the estimator's acceptance, its linked markup ids, and the finish tags those markups are attached to — the scopes the question touches. withdrawn[] lists the numbers delete_rfi tombstoned, so a gap in the sequence is explained rather than silent. Read this before raising a question the register already holds.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {},
  "type": "object"
}
sha256:73fc3af6ba54a1293c44f954cf944c40d069a764ef7974e6fc74addd4231b225

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "count": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "open": {
      "description": "Still awaiting an answer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "pending": {
      "description": "Agent-raised and not yet accepted by an estimator",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "rfis": {
      "description": "Every live RFI, register order",
      "items": {
        "additionalProperties": false,
        "properties": {
          "actor": {
            "description": "Who raised it — \"agent\" for every RFI minted over MCP, \"estimator\" for a panel-raised one",
            "enum": [
              "agent",
              "estimator"
            ],
            "type": "string"
          },
          "conditions": {
            "description": "Finish tags the linked markups are attached to — the scopes this question touches",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "date": {
            "description": "YYYY-MM-DD opened",
            "type": "string"
          },
          "id": {
            "description": "The record id (\"rfi-…\")",
            "type": "string"
          },
          "linked_markups": {
            "description": "Annotation ids carrying this RFI's number on the sheet (markup.rfi_id) — derived, never stored twice",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "number": {
            "description": "The register number, \"RFI-001\" — next in the panel's own sequence, never reissued",
            "type": "string"
          },
          "pending": {
            "description": "true = agent-raised and not yet accepted by an estimator in the register (origin.reviewed false) — pencil, not sent",
            "type": "boolean"
          },
          "question": {
            "type": "string"
          },
          "response": {
            "type": "string"
          },
          "response_date": {
            "description": "YYYY-MM-DD answered, '' while open",
            "type": "string"
          },
          "sheet": {
            "description": "The sheet the question is about",
            "type": "string"
          },
          "status": {
            "description": "The panel's lifecycle: open → answered → closed; void = withdrawn",
            "enum": [
              "open",
              "answered",
              "closed",
              "void"
            ],
            "type": "string"
          },
          "subject": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "number",
          "subject",
          "question",
          "status",
          "sheet",
          "actor",
          "pending",
          "date",
          "response",
          "response_date",
          "linked_markups",
          "conditions"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "withdrawn": {
      "description": "Numbers of withdrawn RFIs (delete_rfi tombstones) — the gaps in the sequence, explained",
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "rfis",
    "count",
    "open",
    "pending",
    "withdrawn"
  ],
  "type": "object"
}
sha256:0e3e0bfeb5733d008c6146c526cbc0caa5b6ef3c1d8578da646400901c747db3

Description hash: sha256:73d702158d0e1c52dbe601f9c9b08a96290dd78ac72644963e693edf8d739cf3

Interface hash: sha256:6af4dbd822b9e6fe030886f0aac369a79fe149463ac17c320dc99f247ad1dbed

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/list_rfis",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "list_rfis"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:4417121f6d954d851daf61bedc2e5429afd61d311ac3b1119851b99e2796b792"
}
toolunknown0.9.990.9.100
list_shapeskentucky-ai-opentakeoff:tool:list_shapes
Observed interface and hashes

The mid-session shape inventory (#149): every committed shape's id, sheet, condition tag, role, quantities, room label, vertex count, and review state in one compact read — the ids edit_shape and delete_shape assume you have, without pulling the whole export_takeoff payload to find one shape. Filter by sheet, by condition, or both; filters narrow, an empty list is a result, not an error.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Only shapes under this finish tag (must exist)",
      "type": "string"
    },
    "sheet": {
      "description": "Only shapes on this sheet",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:57f75b70c37ba83bbff4c8c57186b5fada9f7acd03f66dc64fdb2afdf1ca8253

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "count": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shapes": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "agent_edits": {
            "description": "Present when the agent has revised this shape",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "area_sf": {
            "type": "number"
          },
          "assignment": {
            "description": "Where the finish tag came from: \"schedule\" = resolved from the room's own schedule row, \"asserted\" = the agent chose it. origin.assignment in export_takeoff carries the citation. Absent on human canvas shapes",
            "enum": [
              "schedule",
              "asserted"
            ],
            "type": "string"
          },
          "condition": {
            "type": "string"
          },
          "count": {
            "type": "number"
          },
          "height_ft": {
            "description": "surface_area shapes — the height they were quantified at",
            "type": "number"
          },
          "id": {
            "type": "string"
          },
          "label": {
            "description": "The room (or phase/area) this shape belongs to — detect_rooms stamps the room number it traced from; edit_shape sets or clears it. Absent when unlabeled",
            "type": "string"
          },
          "measure_role": {
            "enum": [
              "floor_area",
              "deduct",
              "linear",
              "surface_area",
              "count"
            ],
            "type": "string"
          },
          "nverts": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "perimeter_lf": {
            "type": "number"
          },
          "proposal_id": {
            "description": "The propose_takeoff batch this shape was committed under (#365) — present on shapes committed while a proposal was open; an accepted shape keeps it as history",
            "type": "string"
          },
          "reviewed": {
            "description": "true = human-affirmed ink, refused by every agent mutation",
            "type": "boolean"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "sheet",
          "condition",
          "measure_role",
          "nverts",
          "reviewed"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "shapes",
    "count"
  ],
  "type": "object"
}
sha256:80bea7811b104ffdbc2b9cf7ed7fdfcaf68c5ff6b7453d82293ca31238ca3497

Description hash: sha256:9d888a1877cc0263a6ea57f3056d70fba65cb544cb506f6a241f5611244b6734

Interface hash: sha256:dda02f11338f252993f0abaa9cca778c6d1af89fea5f09402fb284d2bc7eb10f

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/list_shapes",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "list_shapes"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:5d053c5741b938ddffc64bb36b2b64a800aa1310b0a2ed2ab1dd0fe4a081572c"
}
toolunknown0.9.990.9.100
load_plankentucky-ai-opentakeoff:tool:load_plan
Observed interface and hashes

Open a plan PDF from disk. Default: replace the whole session (previous documents, scales, conditions, and shapes are cleared). merge: true ADDS the document to the working set instead (#152) — a bid set is plans + schedule + addenda, not one PDF — keeping every scale, condition, and shape; sheet keys carry file names so documents never collide, the sheet graph spans the whole set (resolve_tag can chain a plan tag on one file to a schedule row in another), and the marked set covers every worked sheet. Re-loading an already-merged file is refused — reload = replace, deliberately. Returns file, files, page_count, and one entry per sheet. The loaded sheets also become browsable resources (takeoff://sheets). Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "merge": {
      "description": "true = ADD this document to the working set, keeping all existing work (merge into an empty session is just a load)",
      "type": "boolean"
    },
    "path": {
      "description": "Path to a plan PDF on disk",
      "type": "string"
    }
  },
  "required": [
    "path"
  ],
  "type": "object"
}
sha256:df6047a1e0774d003d51cd961e2c5fae6b516332bad1658d2f82213b1ef165cf

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "file": {
      "description": "The document just loaded (basename)",
      "type": "string"
    },
    "files": {
      "description": "Every document in the working set, load order (#152 — one entry unless merge was used)",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "note": {
      "type": "string"
    },
    "page_count": {
      "description": "Total sheets across the working set",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "sheets": {
      "description": "EVERY sheet in the working set, not just the file loaded by this call",
      "items": {
        "additionalProperties": false,
        "properties": {
          "detected_scale": {
            "description": "Drawn scale note read off the sheet — a suggestion, never auto-applied",
            "type": "string"
          },
          "height_pt": {
            "type": "number"
          },
          "height_px": {
            "type": "number"
          },
          "page": {
            "description": "1-based page number",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "sheet": {
            "description": "Sheet key: page 1 is the bare file name (\"plan.pdf\"), pages 2+ are \"plan.pdf#2\"",
            "type": "string"
          },
          "sheet_number": {
            "description": "Title-block sheet number (\"A-101\") where detected",
            "type": "string"
          },
          "width_pt": {
            "type": "number"
          },
          "width_px": {
            "description": "Image px at render scale 2.0 — the coordinate space every tool speaks",
            "type": "number"
          }
        },
        "required": [
          "sheet",
          "page",
          "width_pt",
          "height_pt",
          "width_px",
          "height_px"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "file",
    "files",
    "page_count",
    "sheets",
    "note"
  ],
  "type": "object"
}
sha256:77382093bb29ea9ab440f2cce646324d895009877d7c29ff70022eff3264eb62

Description hash: sha256:e6e89a826bae4e816cfeb6fdda82ffde3e4a071c60a7f5c4fdf3b2a9954b9e04

Interface hash: sha256:3461f3abba70d99ea683be02ffefda997c4d2e99fabcc0e9a6f05da87c625960

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/load_plan",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "load_plan"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:785008b93a6db73a74980913134ca98150318fbdd81b221755d804c67f5f7a5c"
}
toolunknown0.9.990.9.100
mark_verdictkentucky-ai-opentakeoff:tool:mark_verdict
Observed interface and hashes

Mark the agent's VERDICT on work — the pencil half of the approval family, and the only half an agent can mint. Two actors exist on the record: the estimator's APPROVED ring is ink, minted solely by a human's click at the canvas's Approve tool; this tool mints the AGENT diamond and structurally nothing else — it takes no actor input to misuse. Target the work either way: shape_id anchors the mark ON a committed shape (a room at its area centroid, a run at its on-path midpoint, a count marker at its point) and records WHAT was marked — the shape_id stays on the record as provenance, and the glyph keeps its own anchor even if the shape is later deleted; or sheet + at drops the mark at a sheet point (image px). Exactly one target. Optional text rides the record through every export; the glyph itself always reads AGENT. A verdict touches no quantity and gates nothing: it is the agent's signed claim that it checked this work — pencil beside the estimator's ink, never in its place. The mark renders as the graphite AGENT diamond on the canvas and in the marked set, the marked-set cover tallies the split ("Approval stamps: N estimator-approved · M agent-marked"), and the record rides the annotations payload through export_takeoff / import_takeoff and the app's own saves. One mark per shape (re-mark = delete_verdict, then mark again); list_annotations returns the inventory in verdicts[]; undo_last steps over a mark exactly like any other mutation. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "at": {
      "additionalItems": false,
      "description": "Sheet-point mode: where the AGENT diamond renders (image px)",
      "items": [
        {
          "type": "number"
        },
        {
          "type": "number"
        }
      ],
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "shape_id": {
      "description": "Mark a committed shape (list_shapes has the ids) — anchored on the shape, recorded as provenance. Exactly one target: this OR sheet + at",
      "type": "string"
    },
    "sheet": {
      "description": "Sheet-point mode: the sheet, together with at",
      "type": "string"
    },
    "text": {
      "description": "Optional short note riding the record and every export — the glyph always reads AGENT",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:a1910f01493ab8c880a7bdf5a22eb77246f6ae18f83d843ee88d76fe83bf2cc3

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "actor": {
      "const": "agent",
      "description": "Always agent — this tool is structurally incapable of minting the estimator's seal",
      "type": "string"
    },
    "at": {
      "additionalItems": false,
      "description": "Where the AGENT diamond renders (image px) — absent only when the marked shape rides a sheet from a file this session hasn't loaded (#152)",
      "items": [
        {
          "type": "number"
        },
        {
          "type": "number"
        }
      ],
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "condition": {
      "description": "Shape mode: the marked shape's finish tag, resolved",
      "type": "string"
    },
    "id": {
      "description": "The minted record id (\"apr-…\")",
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "shape_id": {
      "description": "Shape mode: the committed shape this verdict is about",
      "type": "string"
    },
    "sheet": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "ts": {
      "description": "ISO-8601 mint time",
      "type": "string"
    }
  },
  "required": [
    "id",
    "actor",
    "sheet",
    "ts",
    "note"
  ],
  "type": "object"
}
sha256:ec0ec75bf8d6f5733de6b5359d763b170aac2732260abb3cdc22f9191642329f

Description hash: sha256:4f21e60a27a4b95291d174d9c92039b97a1cb9b62bd632d75a71ade268afdd5d

Interface hash: sha256:99b1098fbdbbd6425ac61093f8063cb5e78469be6a49eeedc89ed13e9ddc7042

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/mark_verdict",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "mark_verdict"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:ba4bc97565890c3c2feab3091a4a69b053017c6601fa6e578381e1508cd0f5f1"
}
toolunknown0.9.990.9.100
measure_linekentucky-ai-opentakeoff:tool:measure_line
Observed interface and hashes

Measure an open polyline (min 2 points, image px): length_lf at the sheet's scale. Requires the scale to be set. Pass condition to commit it as a linear shape (base, transitions, feature strips, conduit and home runs). A curved run (base along a radius wall, a curved feature strip) takes arc_through: one point on the bow, marked. DROP AND RISE (#441): a plan trace is the flat X–Y path; the material also travels VERTICALLY — a home run drops from the ceiling to a panel, rises to a box. length_lf is the TOTAL: plan + rise + drop. The condition's rise_ft / drop_ft (edit_condition) are the defaults for every run under it; pass rise_ft / drop_ft here to give THIS run its own legs (0 included — "no drop on this one" is a statement), and the reply splits plan_lf / vertical_lf beside the total when a leg exists. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "arc_through": {
      "description": "Indices of points that are the MIDDLE of an arc: the trace runs the point before → this point → the point after as the unique circle through the three (the canvas's Curve mode). For a curved wall put one point anywhere ON the bow between its two ends and mark it. The arc is baked to ordinary vertices on commit and origin.curved is stamped; a mark on an end of an open run, or two marks in a row, refuses.",
      "items": {
        "maximum": 9007199254740991,
        "minimum": 0,
        "type": "integer"
      },
      "type": "array"
    },
    "condition": {
      "type": "string"
    },
    "drop_ft": {
      "description": "This run's vertical leg DOWN, in feet, added to its plan length — overrides the condition's drop_ft default for this run (0 = no drop here, whatever the default)",
      "minimum": 0,
      "type": "number"
    },
    "pts": {
      "items": {
        "additionalItems": false,
        "items": [
          {
            "type": "number"
          },
          {
            "type": "number"
          }
        ],
        "maxItems": 2,
        "minItems": 2,
        "type": "array"
      },
      "minItems": 2,
      "type": "array"
    },
    "rise_ft": {
      "description": "This run's vertical leg UP, in feet, added to its plan length — overrides the condition's rise_ft default for this run (0 = no rise here, whatever the default)",
      "minimum": 0,
      "type": "number"
    },
    "sheet": {
      "type": "string"
    }
  },
  "required": [
    "sheet",
    "pts"
  ],
  "type": "object"
}
sha256:0ee00992834c47537929211f043d16f59790b43e99ba28e268976b3a6c86a775

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "arcs": {
      "description": "How many arc_through bows were laid — present only when the trace was bent; the vertices reported are the baked arc, not the three points you gave",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "drop_ft": {
      "description": "The drop this run resolved to — present with vertical_lf",
      "type": "number"
    },
    "length_lf": {
      "description": "The run's TOTAL length: plan trace + rise + drop (#441)",
      "type": "number"
    },
    "npts": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "plan_lf": {
      "description": "The flat X–Y trace alone — present only when the run carries a vertical leg",
      "type": "number"
    },
    "rise_ft": {
      "description": "The rise this run resolved to (its own, else the condition default) — present with vertical_lf",
      "type": "number"
    },
    "shape_id": {
      "description": "Present when condition was passed and the shape committed",
      "type": "string"
    },
    "vertical_lf": {
      "description": "rise_ft + drop_ft — present only when a leg exists",
      "type": "number"
    }
  },
  "required": [
    "length_lf",
    "npts"
  ],
  "type": "object"
}
sha256:3c0229bb917e8ae25661b1e373365ec747f1c1be51ed88ada217d7b74851ef76

Description hash: sha256:922ada486b841e666bed0cbcd390745e23c1b587661c3a3940cdc14c559dde2d

Interface hash: sha256:81a49e4e2d98e68548c880c47aea0ba5dd9050a95002ff9570609b86427628b6

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/measure_line",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "measure_line"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:b45134578c34192e731e46e99dd6a3ae3c991f1f8d5e792cc644a9e1d23dccbd"
}
toolunknown0.9.990.9.100
measure_polygonkentucky-ai-opentakeoff:tool:measure_polygon
Observed interface and hashes

Measure a closed polygon you supply (min 3 vertices, image px): area_sf and perimeter_lf at the sheet's scale. Requires the scale to be set. Pass condition to commit it; role "deduct" subtracts. A room ring belongs on the innermost wall-face strokes from get_sheet_vectors, crossing each door opening on the wall centerline and wrapping columns and stubs; never on a hatch edge, casework or a door leaf. Check it with view_sheet overlay:true on a tight crop and fix it with edit_shape. A CURVED wall is a circle: do not chord it and do not hand-tessellate it — give the bow one point on the wall and list its index in arc_through. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "arc_through": {
      "description": "Indices of points that are the MIDDLE of an arc: the trace runs the point before → this point → the point after as the unique circle through the three (the canvas's Curve mode). For a curved wall put one point anywhere ON the bow between its two ends and mark it. The arc is baked to ordinary vertices on commit and origin.curved is stamped; a mark on an end of an open run, or two marks in a row, refuses.",
      "items": {
        "maximum": 9007199254740991,
        "minimum": 0,
        "type": "integer"
      },
      "type": "array"
    },
    "condition": {
      "type": "string"
    },
    "role": {
      "default": "floor_area",
      "enum": [
        "floor_area",
        "deduct"
      ],
      "type": "string"
    },
    "sheet": {
      "type": "string"
    },
    "verts": {
      "items": {
        "additionalItems": false,
        "items": [
          {
            "type": "number"
          },
          {
            "type": "number"
          }
        ],
        "maxItems": 2,
        "minItems": 2,
        "type": "array"
      },
      "minItems": 3,
      "type": "array"
    }
  },
  "required": [
    "sheet",
    "verts"
  ],
  "type": "object"
}
sha256:e4051c5a0ea03c422b61db7b6f5d0d13fda2a7813be3f3694b4fee87d27c64b4

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "arcs": {
      "description": "How many arc_through bows were laid — present only when the trace was bent; the vertices reported are the baked arc, not the three points you gave",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "area_sf": {
      "type": "number"
    },
    "nverts": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "perimeter_lf": {
      "type": "number"
    },
    "shape_id": {
      "description": "Present when condition was passed and the shape committed",
      "type": "string"
    },
    "warning": {
      "description": "Mixed-scale warning (#153): a scale note disagreeing with the sheet's sits in the measured region — verify before trusting these numbers",
      "type": "string"
    }
  },
  "required": [
    "area_sf",
    "perimeter_lf",
    "nverts"
  ],
  "type": "object"
}
sha256:0077cc335ff781bf873def61b7da5b1e32c259aee0130bf17b39684a40ee68aa

Description hash: sha256:3663e5c0aee7db4200f4f37509c3a5775b96ac60015c208219cbd07342062efc

Interface hash: sha256:14d3195ff82bb068048db4965dde9e8ded5dd00964fb23538a1be0d33c54f091

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/measure_polygon",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "measure_polygon"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:569a2de407a87138d7ed4776f9f69898b1e04062d195c0bc7fe08ca8dd246f15"
}
toolunknown0.9.990.9.100
measure_surfacekentucky-ai-opentakeoff:tool:measure_surface
Observed interface and hashes

Surface Area — wall SF (#146): trace an OPEN run along the wall in plan view (min 2 points, image px) and the quantity is traced LF × height. This is how wall tile, wainscot, and wall systems are taken off — the quantity family measure_polygon cannot produce. Height lives on the CONDITION (the canvas's H knob): pass height_ft to set it on this call (journals as its own undo step, like typing H before tracing), or set it once with edit_condition; with neither, this refuses and mints nothing. The shape snapshots the height it was quantified at. Requires the sheet's scale. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "arc_through": {
      "description": "Indices of points that are the MIDDLE of an arc: the trace runs the point before → this point → the point after as the unique circle through the three (the canvas's Curve mode). For a curved wall put one point anywhere ON the bow between its two ends and mark it. The arc is baked to ordinary vertices on commit and origin.curved is stamped; a mark on an end of an open run, or two marks in a row, refuses.",
      "items": {
        "maximum": 9007199254740991,
        "minimum": 0,
        "type": "integer"
      },
      "type": "array"
    },
    "condition": {
      "description": "Finish tag to commit under (minted on first use), e.g. 'CT-W1'",
      "type": "string"
    },
    "height_ft": {
      "description": "Wall height in feet — written to the condition's H knob first, then used",
      "exclusiveMinimum": 0,
      "type": "number"
    },
    "pts": {
      "description": "The wall run, an open polyline (image px)",
      "items": {
        "additionalItems": false,
        "items": [
          {
            "type": "number"
          },
          {
            "type": "number"
          }
        ],
        "maxItems": 2,
        "minItems": 2,
        "type": "array"
      },
      "minItems": 2,
      "type": "array"
    },
    "sheet": {
      "type": "string"
    }
  },
  "required": [
    "sheet",
    "pts",
    "condition"
  ],
  "type": "object"
}
sha256:a99a6f42a09f8ec87bbdb9f2ace9e7be0f529f0d4b3a1b8dde74c12cefbd23f0

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "arcs": {
      "description": "How many arc_through bows were laid — present only when the trace was bent; the vertices reported are the baked arc, not the three points you gave",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "area_sf": {
      "description": "length_lf × height_ft — the wall SF committed",
      "type": "number"
    },
    "condition": {
      "type": "string"
    },
    "height_ft": {
      "description": "The height this shape was quantified at (snapshotted on the shape)",
      "type": "number"
    },
    "length_lf": {
      "description": "The traced run's open length",
      "type": "number"
    },
    "npts": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shape_id": {
      "type": "string"
    }
  },
  "required": [
    "condition",
    "height_ft",
    "length_lf",
    "area_sf",
    "npts",
    "shape_id"
  ],
  "type": "object"
}
sha256:7fe9d44449d6b00464165ea7cedf69fb8f1e57cfa3991fb60777a61570d29de7

Description hash: sha256:e71d7b6198902859bcf8035b84ed1cfcf588b45831d122599a0e620329aef91a

Interface hash: sha256:0677cf70bc42c2be5cffa1d1e2ea9207e1dd62b61508aae83515b62fbe3d2789

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/measure_surface",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "measure_surface"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:59c9fe77a2c4933dd33d1ea6d2d9fbd2cbcc880bf4a64db3e3f52e9dac626ba4"
}
toolunknown0.9.990.9.100
open_suitekentucky-ai-opentakeoff:tool:open_suite
Observed interface and hashes

Open a trade suite: enables that trade's tools (they are hidden until opened) and returns its method and condition names. Open only the trade you are taking off; opening is idempotent and never closes anything. No arguments = the catalog. Suites: - finishes (Div 09): flooring, base, transitions, wall finishes: core tools, no extra tools - roofing (Div 07): sloped roof area and squares, true rake/hip/valley LF, drip edge, starter, ridge cap, underlayment - siding (Div 07): net wall area and squares from elevations, opening trim, starter, corners, lap pieces - soffit_fascia (Div 07): soffit SF from eave/rake LF × depth, fascia LF, wall receiver, attic intake vent area - glazing (Div 08): storefront / curtain wall: frame SF, lites, glass SF, mullion LF, perimeter sealant - doors (Div 08): doors per type and size from the door schedule, matched to tags on the plans: core tools - plumbing (Div 22): fixture counts checked against the schedule QTY, pipe LF by system/size, hangers, fittings, insulation - electrical (Div 26/27/28): legend devices and fixtures counted, conduit LF with drops, wire LF by conductors, boxes, whips division opens every suite of a CSI division ("07" = roofing + siding + soffit_fascia).

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "division": {
      "description": "CSI division, e.g. \"07\", \"08\", \"22\", \"26\"",
      "type": "string"
    },
    "suite": {
      "description": "Suite id",
      "enum": [
        "finishes",
        "roofing",
        "siding",
        "soffit_fascia",
        "glazing",
        "doors",
        "plumbing",
        "electrical"
      ],
      "type": "string"
    }
  },
  "type": "object"
}
sha256:efceada91ae030c92a69c9436d699babed83ac711bbb48c9f906561a83a92370

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "catalog": {
      "description": "Every suite, one row each, when called without suite/division",
      "items": {
        "additionalProperties": {},
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    },
    "next": {
      "type": "string"
    },
    "open_suites": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "opened": {
      "description": "Suites opened by this call (empty when listing)",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "suites": {
      "description": "Each opened suite's method and condition presets",
      "items": {
        "additionalProperties": {},
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    },
    "tools_enabled": {
      "description": "Tools that just became available",
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "opened",
    "tools_enabled",
    "open_suites",
    "next"
  ],
  "type": "object"
}
sha256:8e78e6cbe609bde20888e37ec8b08cc823386b99353c21bf83a3787aea0fc713

Description hash: sha256:b276938feb7d054e88426cfb20e2833ee7e7bdab0692acf5923258dc067c032d

Interface hash: sha256:c852074a7c15bb3b2b8fa5e00a0b5843426183d5d0d04cfa4d1207cbf99ce01b

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/open_suite",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "open_suite"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:0343a5eb1fb140836b61d67a4df0df8a2ae3fd9508914b94094f471b6261a257"
}
toolunknown0.9.1050.9.105
place_countkentucky-ai-opentakeoff:tool:place_count
Observed interface and hashes

Count markers — EA (#146): one point, one each. Thresholds, stair nosings, floor boxes, entrance mats — the scale-free quantity family. Commits one count shape per point (computed {count: 1}, exactly the canvas's Count tool), NO scale required, and the whole call is ONE undo step. takeoff_summary reports them as ea; the marked set draws each marker. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Finish tag to commit under (minted on first use), e.g. 'TR-1'",
      "type": "string"
    },
    "points": {
      "description": "Marker positions (image px), one committed count shape each",
      "items": {
        "additionalItems": false,
        "items": [
          {
            "type": "number"
          },
          {
            "type": "number"
          }
        ],
        "maxItems": 2,
        "minItems": 2,
        "type": "array"
      },
      "minItems": 1,
      "type": "array"
    },
    "sheet": {
      "type": "string"
    }
  },
  "required": [
    "sheet",
    "points",
    "condition"
  ],
  "type": "object"
}
sha256:918edd1130d5bba175fea21a6cb28fe52db3490e6bc1315cfac8f447ce36b2e6

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "committed": {
      "description": "Count shapes committed by this call — one per point",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "condition": {
      "type": "string"
    },
    "ea_total": {
      "description": "The condition's total EA after this call",
      "type": "number"
    },
    "shape_ids": {
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "committed",
    "shape_ids",
    "condition",
    "ea_total"
  ],
  "type": "object"
}
sha256:43c2fd1280265609f559911d9b7abecfa78623ac6dbbcb45cf33496069380ee7

Description hash: sha256:46f176aebc4dff242a54df6e541d0e87904f53a9ce2e18d761d37f15bd37bdc1

Interface hash: sha256:c1612d0e667c8473c18bcfba5ec7c82c6813f27262f32309a0529e39d383fd4d

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/place_count",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "place_count"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:8bad719e94357dacbac6fcc13e7ac621f6680bd914f44a8a66ca13b3b53eb99f"
}
toolunknown0.9.990.9.100
propose_condition_editkentucky-ai-opentakeoff:tool:propose_condition_edit
Observed interface and hashes

PROPOSE a change to a condition instead of making it (#365): a diff — a new finish tag (rename), waste %, ×N multiplier, height_ft, roll_setup — held PENDING until the estimator accepts it from the panel. edit_condition is the wrong power for "I think this condition is wrong": a tag rename or a knob change should be a decision the estimator makes, not one they discover. Until acceptance NOTHING changes — takeoff_summary and export_report keep computing from the current values and carry the diff beside them (proposed_condition_edits), and once accepted the report is byte-for-byte what a direct edit_condition would have produced (the same write path). Only fields that differ from the current value are recorded; a proposal that changes nothing is refused, and a rename onto a tag another condition already carries is refused (two conditions on one tag would make one unreachable). One pending diff per condition — proposing again replaces the earlier one (undo_last restores it). rationale is required: the estimator accepts a reason.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Finish tag of an EXISTING condition, e.g. 'CPT-1'",
      "type": "string"
    },
    "drop_ft": {
      "description": "Proposed default vertical leg DOWN for the condition's linear runs (#441)",
      "minimum": 0,
      "type": "number"
    },
    "finish_tag": {
      "description": "Proposed new tag (a rename)",
      "minLength": 1,
      "type": "string"
    },
    "height_ft": {
      "exclusiveMinimum": 0,
      "type": "number"
    },
    "multiplier": {
      "exclusiveMinimum": 0,
      "type": "number"
    },
    "rationale": {
      "description": "Why — the schedule row, the spec section, the sheet note that decided it",
      "minLength": 1,
      "type": "string"
    },
    "rise_ft": {
      "description": "Proposed default vertical leg UP for the condition's linear runs (#441)",
      "minimum": 0,
      "type": "number"
    },
    "roll_setup": {
      "anyOf": [
        {
          "type": "null"
        },
        {
          "additionalProperties": {},
          "properties": {},
          "type": "object"
        }
      ],
      "description": "Proposed roll-goods setup, or null to propose opting out"
    },
    "waste_pct": {
      "minimum": 0,
      "type": "number"
    }
  },
  "required": [
    "condition",
    "rationale"
  ],
  "type": "object"
}
sha256:5676db25e35c1cfe832bde3de45f1ea1971292fb9fa037db00b4ec7cd11bf025

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "condition": {
      "type": "string"
    },
    "condition_id": {
      "type": "string"
    },
    "current": {
      "additionalProperties": {},
      "properties": {
        "drop_ft": {
          "type": "number"
        },
        "finish_tag": {
          "type": "string"
        },
        "height_ft": {
          "type": "number"
        },
        "multiplier": {
          "type": "number"
        },
        "rise_ft": {
          "type": "number"
        },
        "roll_setup": {
          "anyOf": [
            {
              "additionalProperties": {},
              "properties": {},
              "type": "object"
            },
            {
              "type": "null"
            }
          ]
        },
        "waste_pct": {
          "type": "number"
        }
      },
      "type": "object"
    },
    "note": {
      "type": "string"
    },
    "proposal_id": {
      "type": "string"
    },
    "proposed": {
      "additionalProperties": {},
      "properties": {
        "drop_ft": {
          "type": "number"
        },
        "finish_tag": {
          "type": "string"
        },
        "height_ft": {
          "type": "number"
        },
        "multiplier": {
          "type": "number"
        },
        "rise_ft": {
          "type": "number"
        },
        "roll_setup": {
          "anyOf": [
            {
              "additionalProperties": {},
              "properties": {},
              "type": "object"
            },
            {
              "type": "null"
            }
          ]
        },
        "waste_pct": {
          "type": "number"
        }
      },
      "type": "object"
    },
    "rationale": {
      "type": "string"
    },
    "replaced_proposal_id": {
      "description": "Present when this proposal replaced an earlier pending one on the same condition",
      "type": "string"
    }
  },
  "required": [
    "proposal_id",
    "condition",
    "condition_id",
    "current",
    "proposed",
    "rationale",
    "note"
  ],
  "type": "object"
}
sha256:5512c9f25b47a95c7280b5506777de2fef7bd61fe3f5e0bc8cc62448cb2875af

Description hash: sha256:d5a2205a282e29f68b51c7db8be30cd8770c989d437f4aac288dc29880340155

Interface hash: sha256:c4499d3d1e18059a85839f531e3dd533b28a9109eb30a8f206998d4cb70abdb0

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/propose_condition_edit",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "propose_condition_edit"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:d44783d91b0e5036a8ef24649413a58dc80e305954633ec0acf95281e76ead08"
}
toolwrite0.9.990.9.100
propose_takeoffkentucky-ai-opentakeoff:tool:propose_takeoff
Observed interface and hashes

Open a PROPOSAL — a named batch of the shapes you are about to commit, with one identity (#365). Every shape you commit from here on (measure_polygon, measure_line, measure_surface, place_count, the sweeps, the derives, cut_out) attaches to it until you open another proposal or withdraw this one; the estimator then sees ONE Accept pill for the whole batch instead of one per shape — a forty-room pass becomes one decision, not forty. Use it BEFORE the work, the way an estimator titles a takeoff before tracing: "Level 2 rooms per finish schedule A-601", "Base derived from CPT-1 rooms". label is what the estimator reads on the pill; rationale is what decided the batch (the schedule row, the sheet, the rule) — both required, neither is a comment. Nothing here commits geometry or changes a total: an empty proposal is just a heading. The batch is what revise_proposal replaces and withdraw_proposal removes; shapes the estimator has already accepted leave the batch and no agent verb reaches them. takeoff_summary carries the ledger (pending / accepted / withdrawn per batch).

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "label": {
      "description": "The batch's title, as the estimator will read it on the Accept pill",
      "minLength": 1,
      "type": "string"
    },
    "rationale": {
      "description": "What decided the batch — cite the schedule row, sheet, or rule",
      "minLength": 1,
      "type": "string"
    }
  },
  "required": [
    "label",
    "rationale"
  ],
  "type": "object"
}
sha256:4ce72852e67282fa68eb0d67aa2c9ce9b0ae042695f2872fe4a84c1dc39725d0

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "label": {
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "proposal_id": {
      "type": "string"
    },
    "rationale": {
      "type": "string"
    }
  },
  "required": [
    "proposal_id",
    "label",
    "rationale",
    "note"
  ],
  "type": "object"
}
sha256:dac0346114f5dd9775bf4430b1d62f58bb4847521220d8a59206cef58082dbc7

Description hash: sha256:3fbbf91210849356be0582448e34c99e45800ba12777f64c2a5576c532db35c6

Interface hash: sha256:4201f6df55335f100dda8bd165da865f161877bea36f6b1fcfc978dcf9d0e1a8

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/propose_takeoff",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "propose_takeoff"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:ea7a87c91f069c2c41370d920b398dc74a14f5fafbbe5d567340c56e35a8af53"
}
toolwrite0.9.990.9.100
read_sheet_textkentucky-ai-opentakeoff:tool:read_sheet_text
Observed interface and hashes

The sheet's text with positions — items [{str, x, y}] in image px plus the joined text. Optionally restrict to a region {x0, y0, x1, y1}. Use it to read title blocks, room labels, finish schedules, and scale notes. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "region": {
      "properties": {
        "x0": {
          "type": "number"
        },
        "x1": {
          "type": "number"
        },
        "y0": {
          "type": "number"
        },
        "y1": {
          "type": "number"
        }
      },
      "required": [
        "x0",
        "y0",
        "x1",
        "y1"
      ],
      "type": "object"
    },
    "sheet": {
      "type": "string"
    }
  },
  "required": [
    "sheet"
  ],
  "type": "object"
}
sha256:a5d68703d180beb10a71a56ccefd752e4824e83cc96165be1de6273e491f0804

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "items": {
      "description": "Positioned text items (image px)",
      "items": {
        "additionalProperties": false,
        "properties": {
          "str": {
            "type": "string"
          },
          "x": {
            "type": "number"
          },
          "y": {
            "type": "number"
          }
        },
        "required": [
          "str",
          "x",
          "y"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "sheet": {
      "type": "string"
    },
    "text": {
      "description": "The items joined with spaces",
      "type": "string"
    }
  },
  "required": [
    "sheet",
    "items",
    "text"
  ],
  "type": "object"
}
sha256:dc479f7c104b4c2b8e9f2a0784f55b137773ccea49767433ef308bca4f63733e

Description hash: sha256:371f9996a495850da706e2d4badd3192231bbe72c9131fe732f33b50e2937bf5

Interface hash: sha256:ef88d67d5b7e05f0462c5aacc04c895fc9ee373e4cc93e56f563ed64ed1143c5

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/read_sheet_text",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "read_sheet_text"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:e3e572d3d100455d81c010a5204c8ecb345feee2870ab1046e9f40b6f520635c"
}
toolunknown0.9.990.9.100
resolve_rfikentucky-ai-opentakeoff:tool:resolve_rfi
Observed interface and hashes

Answer an OPEN RFI: the answer lands as its response, status becomes answered (the register's own state for "response in"), and the response date stamps exactly as the panel's would, plus an ISO timestamp of the resolve. Only an open RFI resolves — an answered, closed, or void one is refused rather than re-answered or quietly revived (undo_last reverses your own resolve if the answer was wrong). Record the answer the drawings or the architect actually gave; an RFI is not resolved by guessing.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "answer": {
      "description": "The response — what settles the question",
      "type": "string"
    },
    "rfi_id": {
      "description": "Record id from create_rfi or list_rfis",
      "type": "string"
    }
  },
  "required": [
    "rfi_id",
    "answer"
  ],
  "type": "object"
}
sha256:bad7610e096f38490aac63d7cc9debbf6cc64c4d72594e028ccd733de2c143d8

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "actor": {
      "description": "Who raised it — \"agent\" for every RFI minted over MCP, \"estimator\" for a panel-raised one",
      "enum": [
        "agent",
        "estimator"
      ],
      "type": "string"
    },
    "conditions": {
      "description": "Finish tags the linked markups are attached to — the scopes this question touches",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "date": {
      "description": "YYYY-MM-DD opened",
      "type": "string"
    },
    "id": {
      "description": "The record id (\"rfi-…\")",
      "type": "string"
    },
    "linked_markups": {
      "description": "Annotation ids carrying this RFI's number on the sheet (markup.rfi_id) — derived, never stored twice",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "note": {
      "type": "string"
    },
    "number": {
      "description": "The register number, \"RFI-001\" — next in the panel's own sequence, never reissued",
      "type": "string"
    },
    "pending": {
      "description": "true = agent-raised and not yet accepted by an estimator in the register (origin.reviewed false) — pencil, not sent",
      "type": "boolean"
    },
    "question": {
      "type": "string"
    },
    "resolved_at": {
      "description": "ISO-8601 time of this resolve",
      "type": "string"
    },
    "response": {
      "type": "string"
    },
    "response_date": {
      "description": "YYYY-MM-DD answered, '' while open",
      "type": "string"
    },
    "sheet": {
      "description": "The sheet the question is about",
      "type": "string"
    },
    "status": {
      "description": "The panel's lifecycle: open → answered → closed; void = withdrawn",
      "enum": [
        "open",
        "answered",
        "closed",
        "void"
      ],
      "type": "string"
    },
    "subject": {
      "type": "string"
    }
  },
  "required": [
    "id",
    "number",
    "subject",
    "question",
    "status",
    "sheet",
    "actor",
    "pending",
    "date",
    "response",
    "response_date",
    "linked_markups",
    "conditions",
    "resolved_at",
    "note"
  ],
  "type": "object"
}
sha256:2131a31b80028a9354fc4e8f2c0b9f71df1f06c63db97afeebad3cb8ebeac479

Description hash: sha256:723852ed380de66dd3da6061c7c9854ab99a2897d72f077901bf8103d7d78694

Interface hash: sha256:e2a87b9e75f62b8b46af3dca66e76585a9bc6d33a780e83643dc91c823ed031f

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/resolve_rfi",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "resolve_rfi"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:a355900adebe54d812f8fd24b92177433a80cfbbd475f989552d13d626c29490"
}
toolunknown0.9.990.9.100
resolve_tagkentucky-ai-opentakeoff:tool:resolve_tag
Observed interface and hashes

Resolve ONE room tag across the set (#87): the plan tag → its room-finish schedule row → each finish code's definition in the finish/material schedule, EVERY edge carrying an evidence pointer (sheet + literal text + bbox — pass a bbox to view_sheet to look at the source). Rows carried by a continuation sheet ("… SCHEDULE — CONT'D") resolve exactly like base-sheet rows, citing the sheet the ink is on. The doctrine is refusal over guessing: a room that appears on the plan with no schedule row returns status "unresolved" with the reason (and still cites the plan tag); reused room numbers return "ambiguous" rather than picking one — on a multi-building set the refusal LISTS the candidate rows per building, and a building-qualified tag ("A-134") picks the building the set names. A delta triangle or REV tag on the answering row (or the plan bubble) rides the result as "revisions": the codes returned are the POST-revision answer, but the ink changed under that delta — view_sheet the marker's bbox and check the addendum before pricing. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "tag": {
      "description": "The room tag as drawn, e.g. \"134\" or \"139A\" — or building-qualified on a multi-building set, e.g. \"A-134\" (building A, room 134)",
      "type": "string"
    }
  },
  "required": [
    "tag"
  ],
  "type": "object"
}
sha256:7523c7507b755eed33ac11f1a6129da7baf6b28f312c6df72245109ddc05cb29

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "building": {
      "description": "resolved only — the building whose schedule row answered, when the set names buildings",
      "type": "string"
    },
    "candidates": {
      "description": "unresolved only — every schedule row that COULD have answered (an ambiguous multi-building tag lists one per building; qualify the tag, e.g. \"A-134\", to pick)",
      "items": {
        "additionalProperties": false,
        "properties": {
          "building": {
            "type": "string"
          },
          "key": {
            "type": "string"
          },
          "sheet": {
            "type": "string"
          },
          "table": {
            "type": "string"
          }
        },
        "required": [
          "key",
          "sheet",
          "table"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "finishes": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "code": {
            "type": "string"
          },
          "definition": {
            "additionalProperties": false,
            "description": "The finish/material-schedule row this code chains to, when one exists",
            "properties": {
              "cells": {
                "additionalProperties": {
                  "type": "string"
                },
                "propertyNames": {
                  "type": "string"
                },
                "type": "object"
              },
              "source": {
                "additionalProperties": false,
                "description": "An evidence pointer — the sheet, the literal text, and where it sits (image px). Every edge in the graph carries one; pass the bbox to view_sheet to LOOK at the source.",
                "properties": {
                  "bbox": {
                    "additionalProperties": false,
                    "properties": {
                      "x0": {
                        "type": "number"
                      },
                      "x1": {
                        "type": "number"
                      },
                      "y0": {
                        "type": "number"
                      },
                      "y1": {
                        "type": "number"
                      }
                    },
                    "required": [
                      "x0",
                      "y0",
                      "x1",
                      "y1"
                    ],
                    "type": "object"
                  },
                  "sheet": {
                    "type": "string"
                  },
                  "text": {
                    "type": "string"
                  }
                },
                "required": [
                  "sheet",
                  "text",
                  "bbox"
                ],
                "type": "object"
              }
            },
            "required": [
              "cells",
              "source"
            ],
            "type": "object"
          },
          "source": {
            "additionalProperties": false,
            "description": "An evidence pointer — the sheet, the literal text, and where it sits (image px). Every edge in the graph carries one; pass the bbox to view_sheet to LOOK at the source.",
            "properties": {
              "bbox": {
                "additionalProperties": false,
                "properties": {
                  "x0": {
                    "type": "number"
                  },
                  "x1": {
                    "type": "number"
                  },
                  "y0": {
                    "type": "number"
                  },
                  "y1": {
                    "type": "number"
                  }
                },
                "required": [
                  "x0",
                  "y0",
                  "x1",
                  "y1"
                ],
                "type": "object"
              },
              "sheet": {
                "type": "string"
              },
              "text": {
                "type": "string"
              }
            },
            "required": [
              "sheet",
              "text",
              "bbox"
            ],
            "type": "object"
          },
          "surface": {
            "description": "The schedule column: FLOOR / BASE / WALL / …",
            "type": "string"
          }
        },
        "required": [
          "surface",
          "code",
          "source"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "reason": {
      "description": "unresolved only — WHY (no schedule row / ambiguous / no schedule found). A room that appears on the plan with no row comes back here, never as a silent omission",
      "type": "string"
    },
    "revisions": {
      "description": "resolved only — delta/REV markers on the answering schedule row or the plan bubble. The finishes above are the POST-revision answer, but the ink changed: check the marker (view_sheet its bbox) and the addendum before pricing",
      "items": {
        "additionalProperties": false,
        "description": "A revision marker (delta triangle / 'REV 2' tag) attached to this item: the ink CHANGED under that revision. The value read is the post-revision answer — view_sheet the marker's bbox and check the addendum before pricing",
        "properties": {
          "drawn": {
            "description": "true = a DRAWN delta: a bare digit inside a triangle of linework (the common CAD convention — the text layer carries only the digit; the geometry proved the triangle). The evidence bbox spans digit and triangle",
            "type": "boolean"
          },
          "rev": {
            "type": "string"
          },
          "source": {
            "additionalProperties": false,
            "description": "An evidence pointer — the sheet, the literal text, and where it sits (image px). Every edge in the graph carries one; pass the bbox to view_sheet to LOOK at the source.",
            "properties": {
              "bbox": {
                "additionalProperties": false,
                "properties": {
                  "x0": {
                    "type": "number"
                  },
                  "x1": {
                    "type": "number"
                  },
                  "y0": {
                    "type": "number"
                  },
                  "y1": {
                    "type": "number"
                  }
                },
                "required": [
                  "x0",
                  "y0",
                  "x1",
                  "y1"
                ],
                "type": "object"
              },
              "sheet": {
                "type": "string"
              },
              "text": {
                "type": "string"
              }
            },
            "required": [
              "sheet",
              "text",
              "bbox"
            ],
            "type": "object"
          }
        },
        "required": [
          "rev",
          "source"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "room": {
      "anyOf": [
        {
          "additionalProperties": false,
          "properties": {
            "bbox": {
              "additionalProperties": false,
              "properties": {
                "x0": {
                  "type": "number"
                },
                "x1": {
                  "type": "number"
                },
                "y0": {
                  "type": "number"
                },
                "y1": {
                  "type": "number"
                }
              },
              "required": [
                "x0",
                "y0",
                "x1",
                "y1"
              ],
              "type": "object"
            },
            "building": {
              "description": "The building the room belongs to, when the set names one — its plan sheet's BUILDING/BLDG context, or the tag's own qualifier ('A-134')",
              "type": "string"
            },
            "corroboration": {
              "description": "Why this number is believed to be a room: \"schedule\" (a room-finish row answers for it), \"name\" (a name is drawn with it and the set has no room-finish schedule), or \"name+schedule\"",
              "type": "string"
            },
            "name": {
              "description": "The name span stacked over the tag ('' when none)",
              "type": "string"
            },
            "revision": {
              "additionalProperties": false,
              "description": "A revision marker (delta triangle / 'REV 2' tag) attached to this item: the ink CHANGED under that revision. The value read is the post-revision answer — view_sheet the marker's bbox and check the addendum before pricing",
              "properties": {
                "drawn": {
                  "description": "true = a DRAWN delta: a bare digit inside a triangle of linework (the common CAD convention — the text layer carries only the digit; the geometry proved the triangle). The evidence bbox spans digit and triangle",
                  "type": "boolean"
                },
                "rev": {
                  "type": "string"
                },
                "source": {
                  "additionalProperties": false,
                  "description": "An evidence pointer — the sheet, the literal text, and where it sits (image px). Every edge in the graph carries one; pass the bbox to view_sheet to LOOK at the source.",
                  "properties": {
                    "bbox": {
                      "additionalProperties": false,
                      "properties": {
                        "x0": {
                          "type": "number"
                        },
                        "x1": {
                          "type": "number"
                        },
                        "y0": {
                          "type": "number"
                        },
                        "y1": {
                          "type": "number"
                        }
                      },
                      "required": [
                        "x0",
                        "y0",
                        "x1",
                        "y1"
                      ],
                      "type": "object"
                    },
                    "sheet": {
                      "type": "string"
                    },
                    "text": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "sheet",
                    "text",
                    "bbox"
                  ],
                  "type": "object"
                }
              },
              "required": [
                "rev",
                "source"
              ],
              "type": "object"
            },
            "sheet": {
              "type": "string"
            },
            "tag": {
              "type": "string"
            }
          },
          "required": [
            "tag",
            "name",
            "sheet",
            "bbox"
          ],
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "description": "The plan tag, when the room appears on a plan sheet — cited even when resolution fails. null on a multi-building ambiguity: citing one building's tag would be quietly wrong"
    },
    "sources": {
      "description": "The chain: plan tag → schedule row (the row cites the sheet that CARRIES it — under a continuation that is the CONT'D sheet)",
      "items": {
        "additionalProperties": false,
        "description": "An evidence pointer — the sheet, the literal text, and where it sits (image px). Every edge in the graph carries one; pass the bbox to view_sheet to LOOK at the source.",
        "properties": {
          "bbox": {
            "additionalProperties": false,
            "properties": {
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "sheet": {
            "type": "string"
          },
          "text": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "text",
          "bbox"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "status": {
      "enum": [
        "resolved",
        "unresolved"
      ],
      "type": "string"
    },
    "tag": {
      "type": "string"
    }
  },
  "required": [
    "status",
    "tag",
    "room"
  ],
  "type": "object"
}
sha256:469ca075055b0c6383204dfb71ac2b182184e357f60be23182a524ea26a222d4

Description hash: sha256:e5b8fdb9984dc8768977d35a78727e0a4dca81e3ac959b63c996d75ade2780c7

Interface hash: sha256:e1133896940a57da337914b2f23a2548522349edceac480ac82683859724d013

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/resolve_tag",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "resolve_tag"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:56a27e893a882a96ddbc41bd9e65c1f0ebe200378313c0b9fb470c3554cf581a"
}
toolunknown0.9.990.9.100
revise_proposalkentucky-ai-opentakeoff:tool:revise_proposal
Observed interface and hashes

Replace EVERY still-pending shape in a proposal with a new set, as ONE journal step (#365) — the move for "I re-measured and got a better batch". The old pending shapes go, the replacements commit under the same proposal, and undo_last puts the previous batch back exactly. All-or-nothing: the whole replacement is validated (sheet, scale, vertex count, a height for surface_area) before the first pending shape is removed, so a malformed last shape leaves the batch untouched and the error says which entry and why. Shapes the estimator already accepted are ink — they stay, and they are not part of what this replaces. verts are image px like every other tool; roles and minimums match the measure tools (floor_area/deduct ≥3, linear/surface_area ≥2, count 1). An empty shapes list is refused — withdraw_proposal is the verb for that. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "proposal_id": {
      "description": "The batch, from propose_takeoff",
      "type": "string"
    },
    "shapes": {
      "items": {
        "properties": {
          "condition": {
            "description": "Finish tag — minted on first touch, like measure_polygon",
            "type": "string"
          },
          "height_ft": {
            "description": "surface_area only — the height to quantify at when the condition has none",
            "exclusiveMinimum": 0,
            "type": "number"
          },
          "label": {
            "description": "The room this shape belongs to (per-room reporting)",
            "type": "string"
          },
          "role": {
            "enum": [
              "floor_area",
              "deduct",
              "linear",
              "surface_area",
              "count"
            ],
            "type": "string"
          },
          "sheet": {
            "description": "Sheet key (\"plan.pdf\", \"plan.pdf#2\") or title-block number",
            "type": "string"
          },
          "verts": {
            "description": "Geometry in image px: a ring for areas, a run for linear/surface, one point for a count",
            "items": {
              "additionalItems": false,
              "items": [
                {
                  "type": "number"
                },
                {
                  "type": "number"
                }
              ],
              "maxItems": 2,
              "minItems": 2,
              "type": "array"
            },
            "minItems": 1,
            "type": "array"
          }
        },
        "required": [
          "sheet",
          "condition",
          "role",
          "verts"
        ],
        "type": "object"
      },
      "minItems": 1,
      "type": "array"
    }
  },
  "required": [
    "proposal_id",
    "shapes"
  ],
  "type": "object"
}
sha256:8544ef316f9affe08ab4d160293d6d31d5a76ec3a14bf1c67b5334f56c92abf2

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "committed": {
      "description": "Replacement shapes committed, all attached to the same batch",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "label": {
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "proposal_id": {
      "type": "string"
    },
    "replaced": {
      "description": "Pending shapes removed from the batch",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shape_ids": {
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "proposal_id",
    "label",
    "replaced",
    "committed",
    "shape_ids",
    "note"
  ],
  "type": "object"
}
sha256:e1f93f5829971d0a7a78833fe127e892ed1e2a822cbff497edd4c5d6c8c127f5

Description hash: sha256:0e2347b198e3ccc048d97c45b47ed82b45ea85f71046fcd1578ac050e8d49be0

Interface hash: sha256:23698e777e5180544582a8b947918045f769e64bd14bdd80c59d0306829d10ac

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/revise_proposal",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "revise_proposal"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:79e7a189e099ad4e2e91749f4bbd3b391ff4e2b159daa31c9653b804a13d1a58"
}
toolunknown0.9.990.9.100
scope_duplicateskentucky-ai-opentakeoff:tool:scope_duplicates
Observed interface and hashes

Two conditions claiming the same floor, as a list (#366). Every pair of committed floor_area shapes on one sheet whose EXACT polygon intersection exceeds min_fraction of the smaller shape — with the shared SF, which condition each belongs to, whether the estimator already affirmed either, and a look region to pass to view_sheet {overlay: true}. Pairs on DIFFERENT conditions are collisions: every total downstream counts that floor twice. Pairs on the SAME condition are a double trace (a different bug) and come back in duplicates. shared_floor_sf is the whole compared set's Σ areas − union, counted once per cell no matter how many shapes pile on it — the number takeoff_summary carries and the one that has to read 0 before any total means anything. Machine-precision edge remnants are ignored; a real overlap below 0.01 SF stays listed with an explanatory note. Supporting materials belong in edit_materials coverage rows, not duplicate floor polygons. Deducts and runs are not claims. Read-only; a shape on an unscaled sheet or with a degenerate ring is listed in unmeasured, never counted as zero. Same rule as the room eval's shared-floor gate (iou ≥ 0.5 = the same space claimed twice). Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "min_fraction": {
      "description": "List a pair only when shared ÷ smaller ≥ this (default 0.05 — rings that merely kiss along a wall are not claims; 0 lists every positive overlap above machine-precision noise)",
      "maximum": 1,
      "minimum": 0,
      "type": "number"
    },
    "sheet": {
      "description": "Restrict to one sheet; default every sheet with floor shapes",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:754c8ded67168567d8c87f150af713eeae1f73a7ac8f4e4293e9218528b39bcf

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "by_sheet": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "shared_floor_sf": {
            "type": "number"
          },
          "sheet_id": {
            "type": "string"
          }
        },
        "required": [
          "sheet_id",
          "shared_floor_sf"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "collisions": {
      "description": "Pairs on DIFFERENT conditions, biggest shared floor first",
      "items": {
        "additionalProperties": false,
        "properties": {
          "a": {
            "additionalProperties": false,
            "properties": {
              "area_sf": {
                "type": "number"
              },
              "condition": {
                "type": "string"
              },
              "condition_id": {
                "type": "string"
              },
              "label": {
                "type": "string"
              },
              "reviewed": {
                "description": "true = the estimator affirmed this shape — ink; scope_merge never trims or deletes it",
                "type": "boolean"
              },
              "shape_id": {
                "type": "string"
              }
            },
            "required": [
              "shape_id",
              "condition_id",
              "condition",
              "area_sf",
              "reviewed"
            ],
            "type": "object"
          },
          "b": {
            "additionalProperties": false,
            "properties": {
              "area_sf": {
                "type": "number"
              },
              "condition": {
                "type": "string"
              },
              "condition_id": {
                "type": "string"
              },
              "label": {
                "type": "string"
              },
              "reviewed": {
                "description": "true = the estimator affirmed this shape — ink; scope_merge never trims or deletes it",
                "type": "boolean"
              },
              "shape_id": {
                "type": "string"
              }
            },
            "required": [
              "shape_id",
              "condition_id",
              "condition",
              "area_sf",
              "reviewed"
            ],
            "type": "object"
          },
          "fraction_of_smaller": {
            "description": "shared ÷ the smaller shape's area (1 = the smaller sits entirely inside the other)",
            "type": "number"
          },
          "iou": {
            "description": "Symmetric intersection-over-union — ≥ 0.5 is the room eval's own 'same space claimed twice' bar",
            "type": "number"
          },
          "look": {
            "additionalProperties": false,
            "description": "Image-px region framing both shapes — pass to view_sheet {overlay: true}",
            "properties": {
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "note": {
            "description": "Explains a positive overlap whose SF rounds to zero",
            "type": "string"
          },
          "same_condition": {
            "description": "true = a double trace on ONE condition (its own list), false = two conditions claiming one floor",
            "type": "boolean"
          },
          "shared_sf": {
            "description": "Polygon intersection through the sheet's scale, rounded to two decimals",
            "type": "number"
          },
          "sheet_id": {
            "type": "string"
          }
        },
        "required": [
          "sheet_id",
          "a",
          "b",
          "shared_sf",
          "fraction_of_smaller",
          "iou",
          "same_condition",
          "look"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "duplicates": {
      "description": "Pairs on the SAME condition — a double trace, a different bug",
      "items": {
        "additionalProperties": false,
        "properties": {
          "a": {
            "additionalProperties": false,
            "properties": {
              "area_sf": {
                "type": "number"
              },
              "condition": {
                "type": "string"
              },
              "condition_id": {
                "type": "string"
              },
              "label": {
                "type": "string"
              },
              "reviewed": {
                "description": "true = the estimator affirmed this shape — ink; scope_merge never trims or deletes it",
                "type": "boolean"
              },
              "shape_id": {
                "type": "string"
              }
            },
            "required": [
              "shape_id",
              "condition_id",
              "condition",
              "area_sf",
              "reviewed"
            ],
            "type": "object"
          },
          "b": {
            "additionalProperties": false,
            "properties": {
              "area_sf": {
                "type": "number"
              },
              "condition": {
                "type": "string"
              },
              "condition_id": {
                "type": "string"
              },
              "label": {
                "type": "string"
              },
              "reviewed": {
                "description": "true = the estimator affirmed this shape — ink; scope_merge never trims or deletes it",
                "type": "boolean"
              },
              "shape_id": {
                "type": "string"
              }
            },
            "required": [
              "shape_id",
              "condition_id",
              "condition",
              "area_sf",
              "reviewed"
            ],
            "type": "object"
          },
          "fraction_of_smaller": {
            "description": "shared ÷ the smaller shape's area (1 = the smaller sits entirely inside the other)",
            "type": "number"
          },
          "iou": {
            "description": "Symmetric intersection-over-union — ≥ 0.5 is the room eval's own 'same space claimed twice' bar",
            "type": "number"
          },
          "look": {
            "additionalProperties": false,
            "description": "Image-px region framing both shapes — pass to view_sheet {overlay: true}",
            "properties": {
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "note": {
            "description": "Explains a positive overlap whose SF rounds to zero",
            "type": "string"
          },
          "same_condition": {
            "description": "true = a double trace on ONE condition (its own list), false = two conditions claiming one floor",
            "type": "boolean"
          },
          "shared_sf": {
            "description": "Polygon intersection through the sheet's scale, rounded to two decimals",
            "type": "number"
          },
          "sheet_id": {
            "type": "string"
          }
        },
        "required": [
          "sheet_id",
          "a",
          "b",
          "shared_sf",
          "fraction_of_smaller",
          "iou",
          "same_condition",
          "look"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "floor_shapes": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "min_fraction": {
      "type": "number"
    },
    "note": {
      "type": "string"
    },
    "shared_floor_sf": {
      "description": "Σ areas − union over the compared floor shapes, counted once per cell",
      "type": "number"
    },
    "unmeasured": {
      "description": "Shapes left out of every number, with the reason — never silently counted as zero",
      "items": {
        "additionalProperties": false,
        "properties": {
          "reason": {
            "type": "string"
          },
          "shape_id": {
            "type": "string"
          },
          "sheet_id": {
            "type": "string"
          }
        },
        "required": [
          "shape_id",
          "sheet_id",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "collisions",
    "duplicates",
    "shared_floor_sf",
    "by_sheet",
    "unmeasured",
    "floor_shapes",
    "min_fraction",
    "note"
  ],
  "type": "object"
}
sha256:ad958844018d45c5b092ed5c8ebd175349957785971eb0cfb696a96ca02ccb75

Description hash: sha256:8d4a2aaf049d71832c0c90464d4308e067f6191f8d2a7447f6cc553f60e9334d

Interface hash: sha256:f12e913ee3d0171cc0d9659f578fe4c76301f643e49fb789771fd2b310f77f66

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/scope_duplicates",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "scope_duplicates"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:97f54f5e8b40cb243e55531c2d35a389271f3561b9e610abdb772bf50ca07863"
}
toolunknown0.9.990.9.100
scope_mergekentucky-ai-opentakeoff:tool:scope_merge
Observed interface and hashes

Resolve ONE collision (#366): given a pair of floor shapes and the winner, the loser gives up the shared floor — TRIMMED to its remainder by an exact boolean difference (the cut_out module's own arithmetic; its quantities re-measured from the result), or DELETED outright when the overlap is near-total (≥ 98% of the loser: the same space claimed twice, not a room with a sliver left). One journal step either way; undo_last restores the loser verbatim. Who wins: state winner; with it omitted the reviewed shape wins over a pending one, and the verb refuses when neither is reviewed (it does not guess which condition the floor belongs to) or when BOTH are (that is the estimator's call — the collision shows on both condition rows in the canvas). The ink rule is absolute: a loser the estimator affirmed is refused whoever you name. A trim that would split the loser into disjoint pieces refuses — that is a re-trace decision, not a merge — and a loser carrying reconciled cutouts refuses (delete the cuts first).

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "shape_a": {
      "description": "One shape of the pair (from scope_duplicates)",
      "type": "string"
    },
    "shape_b": {
      "description": "The other",
      "type": "string"
    },
    "winner": {
      "description": "Which of the two keeps the shared floor; omit to let the reviewed one win",
      "type": "string"
    }
  },
  "required": [
    "shape_a",
    "shape_b"
  ],
  "type": "object"
}
sha256:d50d08c21ae9985eb409c668d67c20c9c3bebead9ff65a845bad3a4293035e3e

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "action": {
      "enum": [
        "trimmed",
        "deleted"
      ],
      "type": "string"
    },
    "loser": {
      "type": "string"
    },
    "loser_after_sf": {
      "type": "number"
    },
    "loser_before_sf": {
      "type": "number"
    },
    "loser_holes": {
      "description": "trimmed: holes the remainder carries (a winner inside the loser leaves one)",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "note": {
      "type": "string"
    },
    "shape_count": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shared_sf": {
      "type": "number"
    },
    "winner": {
      "type": "string"
    }
  },
  "required": [
    "action",
    "winner",
    "loser",
    "shared_sf",
    "loser_before_sf",
    "loser_after_sf",
    "shape_count",
    "note"
  ],
  "type": "object"
}
sha256:96cfce1bffd90eec25c13c22f5bcf47d6745e33b98b2b327af547d0891fe64b3

Description hash: sha256:0986be7c6ddc88166cfcf9aabf1ea67b2d1d6ac8d21496d8a71ca43dd450d509

Interface hash: sha256:971e9cf09635405984a9324e006ff3f055ab355e7202d956f8320adf019afbd2

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/scope_merge",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "scope_merge"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:3006404711809068cc459f93807b737abf1a22960ca9ecefde02d9cc28aa8d05"
}
toolunknown0.9.990.9.100
set_estimate_settingskentucky-ai-opentakeoff:tool:set_estimate_settings
Observed interface and hashes

The project's markups, proposal text and client — the canvas's estimate_settings, bid_proposal and client_info. Markups: tax_pct (sales tax on material), overhead_pct (on material + labor + tax), profit_pct with profit_mode markup (× (1 + p)) or margin (÷ (1 − p); 33.33% margin is ×1.5). proposal: itemized (a sell price on each scope line, the base bid allocated to the cent) or lump sum, scope_note, inclusions / exclusions (one per line), terms, valid_days. client: who the proposal is for. Only what you pass changes; an empty client string clears that field. Until markups are set the estimate prices at 0% — say so rather than assume a number. Every price comes from the estimator or a document they gave you — never invent, estimate or 'typical' one; a price nobody entered stays unentered and estimate_summary names it. Rides export_takeoff; undo_last reverses the call.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "client": {
      "properties": {
        "address": {
          "type": "string"
        },
        "name": {
          "type": "string"
        },
        "reference": {
          "type": "string"
        }
      },
      "type": "object"
    },
    "overhead_pct": {
      "minimum": 0,
      "type": "number"
    },
    "profit_mode": {
      "enum": [
        "markup",
        "margin"
      ],
      "type": "string"
    },
    "profit_pct": {
      "minimum": 0,
      "type": "number"
    },
    "proposal": {
      "properties": {
        "exclusions": {
          "description": "One per line",
          "type": "string"
        },
        "inclusions": {
          "description": "One per line",
          "type": "string"
        },
        "itemized": {
          "type": "boolean"
        },
        "scope_note": {
          "type": "string"
        },
        "terms": {
          "type": "string"
        },
        "valid_days": {
          "maximum": 365,
          "minimum": 1,
          "type": "integer"
        }
      },
      "type": "object"
    },
    "tax_pct": {
      "minimum": 0,
      "type": "number"
    }
  },
  "type": "object"
}
sha256:4e9c6dab69eebc616e1e3f246e6f7c3ff051eca82125872a34d5ba0d2e781c58

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "bid_proposal": {
      "anyOf": [
        {
          "additionalProperties": {},
          "properties": {},
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    },
    "client_info": {
      "additionalProperties": {},
      "properties": {},
      "type": "object"
    },
    "estimate_settings": {
      "anyOf": [
        {
          "additionalProperties": {},
          "properties": {
            "overhead_pct": {
              "type": "number"
            },
            "profit_mode": {
              "enum": [
                "markup",
                "margin"
              ],
              "type": "string"
            },
            "profit_pct": {
              "type": "number"
            },
            "tax_pct": {
              "type": "number"
            }
          },
          "required": [
            "tax_pct",
            "overhead_pct",
            "profit_pct",
            "profit_mode"
          ],
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "estimate_settings",
    "bid_proposal",
    "client_info"
  ],
  "type": "object"
}
sha256:12b44fb13b1c89bcdd52df7368674c5a17e1f52c7ddc634a04db47d5b00f09b2

Description hash: sha256:445bc914e47e9de69e160c23ad8f59cdd36a534c5df8569d77ccad41637f02e0

Interface hash: sha256:277250cf0c23d52fe2a6995a40bf685af675624ddcf8a38efc173b9eb4f1a105

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/set_estimate_settings",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "set_estimate_settings"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:17063e90523e0d87a2bc63069be8dc2e31a66ef3381cef77cf9b97cede72f3ef"
}
toolwrite0.9.990.9.100
set_pricingkentucky-ai-opentakeoff:tool:set_pricing
Observed interface and hashes

Price one condition for the estimate — the canvas Estimate panel's rows. A condition has one estimate line per quantity kind it carries (its area, LF and EA — see estimate_summary); the first is its MAIN line. unit is what the main line is bought in (SF, SY, LF, EA). line picks WHICH line material and labor price: leave it out (or pass the main line's unit) for the main line; pass "LF", "EA" or "SF" (a second area line prices in SF) to price that other line — one call per line. material and labor are $ per that line's unit: material is priced on the ORDER quantity (waste applied — SY is the waste-adjusted SY), labor on the MEASURED quantity (no waste); EA carries no waste on either. materials prices the condition's supporting-material rows (from edit_materials) per THEIR unit (bag, pail, roll) — quantities are already whole packages. null clears a price back to "not entered"; 0 is an explicit $0 (owner-furnished material, labor-only scope). A bordered linear run's derived second line (its LF when the border SF is the main line, or the reverse) is OPTIONAL: it shows and can be priced, but left empty it is carried in the main line, never missing. Every price comes from the estimator or a document they gave you — never invent, estimate or 'typical' one; a price nobody entered stays unentered and estimate_summary names it. The reply carries the line this call priced (line) and all of the condition's lines (lines), with a note naming any line still unpriced. Rides export_takeoff into the app; undo_last reverses the call.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Finish tag of an existing condition, e.g. 'CPT-1'",
      "type": "string"
    },
    "labor": {
      "anyOf": [
        {
          "minimum": 0,
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "description": "Labor $ per unit, on the measured quantity; null clears"
    },
    "line": {
      "description": "Which line material / labor price: omitted or the main line's unit = the main line; LF / EA / SF = the condition's other line of that kind (stored in pricing.by_unit)",
      "enum": [
        "SF",
        "SY",
        "LF",
        "EA"
      ],
      "type": "string"
    },
    "material": {
      "anyOf": [
        {
          "minimum": 0,
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "description": "Material $ per unit, on the order quantity; null clears"
    },
    "materials": {
      "description": "Prices for the condition's supporting-material rows",
      "items": {
        "properties": {
          "name": {
            "description": "A supporting-material row's name on this condition (case-insensitive)",
            "type": "string"
          },
          "price": {
            "anyOf": [
              {
                "minimum": 0,
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "description": "$ per the row's own unit; null clears"
          }
        },
        "required": [
          "name",
          "price"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "unit": {
      "description": "The MAIN line's pricing unit (default: what was measured — area, then length, then count)",
      "enum": [
        "SF",
        "SY",
        "LF",
        "EA"
      ],
      "type": "string"
    }
  },
  "required": [
    "condition"
  ],
  "type": "object"
}
sha256:b2171175b3ac78e6f7588ab0be75ab965e481c89b4936475521c6c62c7da0e23

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "condition": {
      "type": "string"
    },
    "condition_id": {
      "type": "string"
    },
    "line": {
      "anyOf": [
        {
          "additionalProperties": {},
          "properties": {
            "finish_tag": {
              "type": "string"
            },
            "id": {
              "type": "string"
            },
            "key": {
              "description": "\"<condition id>:<unit>\" — one line per quantity kind the condition carries",
              "type": "string"
            },
            "labor_cost": {
              "type": "number"
            },
            "labor_qty": {
              "description": "Measured quantity in the unit — no waste",
              "type": "number"
            },
            "labor_rate": {
              "description": "$ per unit; null = never entered",
              "type": [
                "number",
                "null"
              ]
            },
            "main": {
              "description": "The condition's first line: priced by pricing.unit / material / labor and carrying its assembly items; the others price from pricing.by_unit[unit]",
              "type": "boolean"
            },
            "material_cost": {
              "type": "number"
            },
            "material_qty": {
              "description": "Order quantity in the unit — waste applied (EA never carries waste)",
              "type": "number"
            },
            "material_rate": {
              "description": "$ per unit; null = never entered",
              "type": [
                "number",
                "null"
              ]
            },
            "materials": {
              "items": {
                "additionalProperties": {},
                "properties": {
                  "cost": {
                    "type": "number"
                  },
                  "name": {
                    "type": "string"
                  },
                  "price": {
                    "type": [
                      "number",
                      "null"
                    ]
                  },
                  "priced": {
                    "type": "boolean"
                  },
                  "qty": {
                    "type": "number"
                  },
                  "unit": {
                    "type": "string"
                  }
                },
                "required": [
                  "name",
                  "unit",
                  "qty",
                  "price",
                  "cost",
                  "priced"
                ],
                "type": "object"
              },
              "type": "array"
            },
            "materials_cost": {
              "type": "number"
            },
            "missing": {
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "optional": {
              "description": "A bordered linear run's derived line: priceable, but an empty rate is carried in the main line, never missing",
              "type": "boolean"
            },
            "status": {
              "description": "optional = an optional line nobody priced (not in unpriced)",
              "enum": [
                "priced",
                "partial",
                "unpriced",
                "optional"
              ],
              "type": "string"
            },
            "total": {
              "type": "number"
            },
            "unit": {
              "enum": [
                "SF",
                "SY",
                "LF",
                "EA"
              ],
              "type": "string"
            }
          },
          "required": [
            "id",
            "finish_tag",
            "unit",
            "material_qty",
            "labor_qty",
            "material_rate",
            "labor_rate",
            "material_cost",
            "labor_cost",
            "materials",
            "materials_cost",
            "total",
            "status",
            "missing"
          ],
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "description": "The line this call priced (the main line unless `line` named another), after the write; null while it has no committed quantity of that kind"
    },
    "lines": {
      "description": "Every estimate line of the condition, main first",
      "items": {
        "additionalProperties": {},
        "properties": {
          "finish_tag": {
            "type": "string"
          },
          "id": {
            "type": "string"
          },
          "key": {
            "description": "\"<condition id>:<unit>\" — one line per quantity kind the condition carries",
            "type": "string"
          },
          "labor_cost": {
            "type": "number"
          },
          "labor_qty": {
            "description": "Measured quantity in the unit — no waste",
            "type": "number"
          },
          "labor_rate": {
            "description": "$ per unit; null = never entered",
            "type": [
              "number",
              "null"
            ]
          },
          "main": {
            "description": "The condition's first line: priced by pricing.unit / material / labor and carrying its assembly items; the others price from pricing.by_unit[unit]",
            "type": "boolean"
          },
          "material_cost": {
            "type": "number"
          },
          "material_qty": {
            "description": "Order quantity in the unit — waste applied (EA never carries waste)",
            "type": "number"
          },
          "material_rate": {
            "description": "$ per unit; null = never entered",
            "type": [
              "number",
              "null"
            ]
          },
          "materials": {
            "items": {
              "additionalProperties": {},
              "properties": {
                "cost": {
                  "type": "number"
                },
                "name": {
                  "type": "string"
                },
                "price": {
                  "type": [
                    "number",
                    "null"
                  ]
                },
                "priced": {
                  "type": "boolean"
                },
                "qty": {
                  "type": "number"
                },
                "unit": {
                  "type": "string"
                }
              },
              "required": [
                "name",
                "unit",
                "qty",
                "price",
                "cost",
                "priced"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "materials_cost": {
            "type": "number"
          },
          "missing": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "optional": {
            "description": "A bordered linear run's derived line: priceable, but an empty rate is carried in the main line, never missing",
            "type": "boolean"
          },
          "status": {
            "description": "optional = an optional line nobody priced (not in unpriced)",
            "enum": [
              "priced",
              "partial",
              "unpriced",
              "optional"
            ],
            "type": "string"
          },
          "total": {
            "type": "number"
          },
          "unit": {
            "enum": [
              "SF",
              "SY",
              "LF",
              "EA"
            ],
            "type": "string"
          }
        },
        "required": [
          "id",
          "finish_tag",
          "unit",
          "material_qty",
          "labor_qty",
          "material_rate",
          "labor_rate",
          "material_cost",
          "labor_cost",
          "materials",
          "materials_cost",
          "total",
          "status",
          "missing"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "material_prices": {
      "items": {
        "additionalProperties": {},
        "properties": {
          "name": {
            "type": "string"
          },
          "price": {
            "type": [
              "number",
              "null"
            ]
          },
          "unit": {
            "type": "string"
          }
        },
        "required": [
          "name",
          "unit",
          "price"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "note": {
      "type": "string"
    },
    "pricing": {
      "additionalProperties": {},
      "description": "The condition's prices after this write; an absent field is not entered",
      "properties": {
        "by_unit": {
          "additionalProperties": {
            "additionalProperties": {},
            "properties": {
              "labor": {
                "type": "number"
              },
              "material": {
                "type": "number"
              }
            },
            "type": "object"
          },
          "description": "The other lines' rates, keyed by their unit",
          "propertyNames": {
            "type": "string"
          },
          "type": "object"
        },
        "labor": {
          "type": "number"
        },
        "material": {
          "type": "number"
        },
        "unit": {
          "enum": [
            "SF",
            "SY",
            "LF",
            "EA"
          ],
          "type": "string"
        }
      },
      "type": "object"
    }
  },
  "required": [
    "condition",
    "condition_id",
    "pricing",
    "material_prices",
    "line",
    "lines"
  ],
  "type": "object"
}
sha256:85ae0500a65e96d28581c172b739e32dfcd077f033576bea8670698d8e64344d

Description hash: sha256:e3b2fdeaf5fd041d8f4d1485c5fd05de945eaa80ddbec6345d4688259a1bb728

Interface hash: sha256:0cafb3349ed7443eb83f4ec0a04595c02ca50a3a19bc3888389582cc013755cc

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/set_pricing",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "set_pricing"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:c050daf6caeffb920bfd5c9a46fe3799a6bcebfb6748c3ce48fc0599166f90e4"
}
toolwrite0.9.990.9.105
set_scalekentucky-ai-opentakeoff:tool:set_scale
Observed interface and hashes

Set a sheet's scale — exactly ONE of: label (a standard scale, e.g. '1/4" = 1'-0"'), upp (real feet per image px), calibrate (two points along a known dimension plus its real feet), or use_detected (adopt the drawn scale note read off the sheet). The detected scale is never applied automatically — setting it is always this explicit call. Changing an existing scale recomputes measurements and cutout restore quantities from geometry and records one undo_last step. Counts are unchanged. Human-reviewed dimensional work must be recalibrated in the canvas; scales must be finite and positive. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "calibrate": {
      "description": "Two points (image px) a known real distance apart, and that distance in feet",
      "properties": {
        "feet": {
          "type": "number"
        },
        "p1": {
          "additionalItems": false,
          "items": [
            {
              "type": "number"
            },
            {
              "type": "number"
            }
          ],
          "maxItems": 2,
          "minItems": 2,
          "type": "array"
        },
        "p2": {
          "additionalItems": false,
          "items": [
            {
              "type": "number"
            },
            {
              "type": "number"
            }
          ],
          "maxItems": 2,
          "minItems": 2,
          "type": "array"
        }
      },
      "required": [
        "p1",
        "p2",
        "feet"
      ],
      "type": "object"
    },
    "label": {
      "description": "A standard scale label, exactly as listed in the error on a miss",
      "type": "string"
    },
    "sheet": {
      "type": "string"
    },
    "upp": {
      "description": "Real feet per image px at render scale 2.0",
      "type": "number"
    },
    "use_detected": {
      "const": true,
      "description": "true = adopt the sheet's detected scale",
      "type": "boolean"
    }
  },
  "required": [
    "sheet"
  ],
  "type": "object"
}
sha256:650b0b2b7fb53e6e7de46329fc350318a6b2843a25d9f2c305ff8cfe43ae4c35

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "confirmed": {
      "description": "Always false here: set_scale is the agent surface, and an agent-set scale stays UNCONFIRMED until a human confirms it in the canvas — quantities still flow, wearing the caveat",
      "type": "boolean"
    },
    "label": {
      "description": "The standard scale label, when set by label or detected note",
      "type": "string"
    },
    "sheet": {
      "type": "string"
    },
    "source": {
      "enum": [
        "label",
        "upp",
        "calibrate",
        "detected"
      ],
      "type": "string"
    },
    "upp": {
      "description": "Real feet per image px at render scale 2.0",
      "type": "number"
    },
    "warning": {
      "description": "Present when the sheet carries MULTIPLE distinct scale notes (#153) — enlarged plans/details likely; region measurements under a disagreeing note will warn",
      "type": "string"
    }
  },
  "required": [
    "sheet",
    "upp",
    "source",
    "confirmed"
  ],
  "type": "object"
}
sha256:ea1afb48095ce2a44ba83621c5e306fab392b64aa60425092c50485b8aa77bf4

Description hash: sha256:1051703cff80f00a6f8fdcf584b51ba6f7cd52f3d83fae511c54df5f69e1048e

Interface hash: sha256:350bd1f0b4a90b1ad563e8ee6b16794e988cb1d9d8fbe11c21e01087a163e414

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/set_scale",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "set_scale"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:1ed15a11fed7249bae0f940d92975d3fd110282c1854e7a12e9eb87ac1e33eec"
}
toolunknown0.9.990.9.100
sheet_contextkentucky-ai-opentakeoff:tool:sheet_context
Observed interface and hashes

The sheet's STRUCTURE in one call and one frame: the classified vector segments, the positioned text spans, and the hatch-family instances of a region — everything the engine itself floods against, exposed as data instead of pixels. Use it when you need to REASON about a region rather than look at it: which lines bound this space and at what pen weight, what the region says, and which periodic fill pattern covers it. The join is the point — all three arrive in image px with no reconciliation left to do, and the reply echoes the post-clamp region so passing that same rect to view_sheet gives you the matching render by construction. Hatch families carry a content-derived id (same pattern spec ⇒ same id, anywhere on the sheet), so matching a plan region to a legend swatch is comparing two ids, not guessing from a render — read the legend region, read the room region, match ids, and cite both bboxes as evidence. Decimation is declared, ordered, and counted on every reply: segments shorter than min_len_px drop first (invisible ink), then a max_segments cap applies LONGEST-FIRST so walls survive and hatch strokes go; kept + dropped always reconciles to total_in_region, and whole segments drop with their meta intact — nothing is ever simplified or merged, because these are classified segments and a merge would rewrite the classification. A scan returns has_vector_linework: false with empty vectors — absence of linework, never a claim the region is blank. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "max_segments": {
      "default": 4000,
      "description": "Segment cap, applied longest-first (default 4000). The reply's dropped.cap says exactly what a smaller region would recover",
      "maximum": 20000,
      "minimum": 1,
      "type": "integer"
    },
    "min_len_px": {
      "default": 2,
      "description": "Drop segments shorter than this (default 2 — one PDF point at render scale 2.0, below any pen width). 0 keeps everything",
      "minimum": 0,
      "type": "number"
    },
    "region": {
      "description": "Rect in image px (origin top-left, y down); omit for the full sheet",
      "properties": {
        "x0": {
          "type": "number"
        },
        "x1": {
          "type": "number"
        },
        "y0": {
          "type": "number"
        },
        "y1": {
          "type": "number"
        }
      },
      "required": [
        "x0",
        "y0",
        "x1",
        "y1"
      ],
      "type": "object"
    },
    "sheet": {
      "type": "string"
    }
  },
  "required": [
    "sheet"
  ],
  "type": "object"
}
sha256:091948d23285dfe180c69d04b0f5f32de06264de46a40fcc6b54b59a660a61aa

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "has_vector_linework": {
      "description": "false = a scan: vectors and hatch are empty because there are none, not because the region is blank",
      "type": "boolean"
    },
    "hatch": {
      "additionalProperties": false,
      "properties": {
        "count": {
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "families": {
          "items": {
            "additionalProperties": false,
            "properties": {
              "angle_deg": {
                "description": "Raw mean angle [0, 180) — rides beside the id for tolerance matching at bucket boundaries",
                "type": "number"
              },
              "bbox": {
                "description": "The instance's tight bbox [x0, y0, x1, y1], image px",
                "items": {
                  "type": "number"
                },
                "maxItems": 4,
                "minItems": 4,
                "type": "array"
              },
              "id": {
                "description": "Content hash of the quantized (angle, pitch, pen-width) signature — the SAME id for the same pattern spec anywhere on the sheet, so legend↔plan matching is id === id. Identifies a pattern, not a material; the legend maps pattern → material.",
                "type": "string"
              },
              "pen_w_px": {
                "description": "Modal device pen width of the members",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "pitch_px": {
                "description": "Raw median row pitch, image px",
                "type": "number"
              },
              "rows": {
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "segments": {
                "description": "Member segments in the whole instance",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "segments_in_region": {
                "description": "…of which this many were returned in vectors (post-decimation)",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              }
            },
            "required": [
              "id",
              "angle_deg",
              "pitch_px",
              "pen_w_px",
              "rows",
              "segments",
              "segments_in_region",
              "bbox"
            ],
            "type": "object"
          },
          "type": "array"
        }
      },
      "required": [
        "families",
        "count"
      ],
      "type": "object"
    },
    "page": {
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "region": {
      "description": "The region actually resolved, post-clamp — pass this same rect to view_sheet and the render is in the same frame by construction",
      "items": {
        "type": "number"
      },
      "maxItems": 4,
      "minItems": 4,
      "type": "array"
    },
    "sheet": {
      "type": "string"
    },
    "sheet_px": {
      "items": {
        "type": "number"
      },
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "text": {
      "additionalProperties": false,
      "properties": {
        "count": {
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "spans": {
          "description": "Text with bboxes, image px, same frame as the vectors",
          "items": {
            "additionalProperties": false,
            "properties": {
              "rot": {
                "description": "Run direction in degrees, clockwise, y down — present only when rotated (90/270 = a quarter-turn, e.g. rotated schedule headers)",
                "type": "number"
              },
              "str": {
                "type": "string"
              },
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "str",
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "type": "array"
        }
      },
      "required": [
        "spans",
        "count"
      ],
      "type": "object"
    },
    "vectors": {
      "additionalProperties": false,
      "properties": {
        "dropped": {
          "additionalProperties": false,
          "properties": {
            "cap": {
              "description": "Over max_segments — the SHORTEST went first, so walls survive",
              "maximum": 9007199254740991,
              "minimum": -9007199254740991,
              "type": "integer"
            },
            "short": {
              "description": "Below min_len_px (invisible ink)",
              "maximum": 9007199254740991,
              "minimum": -9007199254740991,
              "type": "integer"
            }
          },
          "required": [
            "short",
            "cap"
          ],
          "type": "object"
        },
        "family": {
          "description": "Aligned with segments: the hatch-family id this segment belongs to, or null for structural linework",
          "items": {
            "type": [
              "string",
              "null"
            ]
          },
          "type": "array"
        },
        "kept": {
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "meta": {
          "description": "One byte per segment, aligned with segments: bit 1 = curve chord, bit 2 = clip-only, bit 4 = filled-not-stroked; high nibble = device pen width",
          "items": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "type": "array"
        },
        "note": {
          "type": "string"
        },
        "segments": {
          "description": "[x0, y0, x1, y1] per segment, image px, endpoints exactly as drawn — clipped by KEEPING whole intersecting segments, never by rewriting them",
          "items": {
            "items": {
              "type": "number"
            },
            "maxItems": 4,
            "minItems": 4,
            "type": "array"
          },
          "type": "array"
        },
        "total_in_region": {
          "description": "Segments intersecting the region before any decimation — kept + dropped always reconciles to this",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "truncated": {
          "type": "boolean"
        }
      },
      "required": [
        "segments",
        "meta",
        "family",
        "kept",
        "total_in_region",
        "truncated",
        "dropped"
      ],
      "type": "object"
    }
  },
  "required": [
    "sheet",
    "page",
    "sheet_px",
    "region",
    "has_vector_linework",
    "vectors",
    "text",
    "hatch"
  ],
  "type": "object"
}
sha256:b71d753fa73a1b4b26e834788eedda6e6e6e39b20ee5e6eb6b912972b0b079da

Description hash: sha256:5ed8d1dc5af5fb9402141d25275c2d94770c4c0551c16861a2bf242573011b2f

Interface hash: sha256:181e22fc53a886c8c9276eab49fb074485aee24eec5509d0d96ebe59bb5f9d3d

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/sheet_context",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "sheet_context"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:ec90769821c7f6ccbfc7d58084681bead59715cad32a507718964cfe0c1f2df0"
}
toolunknown0.9.990.9.100
sheet_graphkentucky-ai-opentakeoff:tool:sheet_graph
Observed interface and hashes

The plan-set INDEX (#87): every sheet's role (plan / schedule / legend / …, with confidence and the title evidence), the schedule tables found (kind, row count, region — a schedule CONTINUED across sheets ("… SCHEDULE — CONT'D") reads as ONE table, the continuation fragment naming its base in "continues"; rotated column headers are read at their quarter-turn and flagged), every number CORROBORATED as a room (with the stacked room NAME when one exists, the room's BUILDING on multi-building sets, and "corroboration" saying why it counts as a room) plus "unmatched_tags" — the numbers that are NOT rooms (keynote hexagons, detail markers, dimension fragments, legend rows), each with a reason, listed and never dropped; READ those reasons, one of them may be a room the schedule left out, the detail callouts (3/A-601 → sheet edges), the set's building designators, every REVISION marker the set carries (text markers "Δ2"/"REV 2" AND drawn deltas — a bare digit inside a triangle of linework, proven from vector geometry and flagged drawn — in "revisions", and attached to the schedule row / room tag they sit on), and named indexing gaps in "notes". Built once per document from the text layer and cached. This is how an agent decides WHAT to measure without a human enumerating the rooms: list the rooms here, resolve each with resolve_tag, then measure with measure_polygon on its wall faces. A scanned set (no text layer) returns available: false — unavailable, never half-populated. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {},
  "type": "object"
}
sha256:73fc3af6ba54a1293c44f954cf944c40d069a764ef7974e6fc74addd4231b225

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "available": {
      "description": "false = the set has no text layer (a scan) — the graph degrades to unavailable, never half-populates",
      "type": "boolean"
    },
    "buildings": {
      "description": "Every building designator the set names (sorted) — present only on multi-building-aware sets. Room numbers reused across these need qualified tags ('A-134')",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "callouts": {
      "description": "Detail callouts (3/A-601) — edges to their target sheets",
      "items": {
        "additionalProperties": false,
        "properties": {
          "bbox": {
            "additionalProperties": false,
            "properties": {
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "detail": {
            "type": "string"
          },
          "sheet": {
            "type": "string"
          },
          "target_sheet": {
            "type": "string"
          }
        },
        "required": [
          "detail",
          "target_sheet",
          "sheet",
          "bbox"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "counts": {
      "additionalProperties": false,
      "properties": {
        "callouts": {
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "rooms": {
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "schedules": {
          "description": "LOGICAL tables — a schedule continued across sheets counts once",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "unmatched_tags": {
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        }
      },
      "required": [
        "rooms",
        "schedules",
        "callouts"
      ],
      "type": "object"
    },
    "notes": {
      "description": "Named gaps found while indexing (e.g. a continuation whose rows could not be aligned) — the graph refuses silently dropping anything",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "revisions": {
      "description": "Every delta-triangle / REV-tag marker the set carries — text markers ('Δ2', 'REV 2') and DRAWN deltas (a bare digit inside a triangle of linework, drawn: true) — where one sits, the ink changed under that revision. Markers on a schedule row or room bubble also attach there (and ride resolve_tag). A revision CLOUD is arc-chain linework these detectors do not read — absence here is not absence of revisions",
      "items": {
        "additionalProperties": false,
        "properties": {
          "bbox": {
            "additionalProperties": false,
            "properties": {
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "drawn": {
            "type": "boolean"
          },
          "rev": {
            "type": "string"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "rev",
          "sheet",
          "bbox"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "rooms": {
      "description": "Numbers CORROBORATED as rooms — a room-finish row answers for them, or (where the set carries no room-finish schedule) a room name is drawn with them. Each says which in `corroboration`. Schedule sheets contribute rows, never phantom rooms",
      "items": {
        "additionalProperties": false,
        "properties": {
          "bbox": {
            "additionalProperties": false,
            "properties": {
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "building": {
            "description": "The building the room belongs to, when the set names one — its plan sheet's BUILDING/BLDG context, or the tag's own qualifier ('A-134')",
            "type": "string"
          },
          "corroboration": {
            "description": "Why this number is believed to be a room: \"schedule\" (a room-finish row answers for it), \"name\" (a name is drawn with it and the set has no room-finish schedule), or \"name+schedule\"",
            "type": "string"
          },
          "name": {
            "description": "The name span stacked over the tag ('' when none)",
            "type": "string"
          },
          "revision": {
            "additionalProperties": false,
            "description": "A revision marker (delta triangle / 'REV 2' tag) attached to this item: the ink CHANGED under that revision. The value read is the post-revision answer — view_sheet the marker's bbox and check the addendum before pricing",
            "properties": {
              "drawn": {
                "description": "true = a DRAWN delta: a bare digit inside a triangle of linework (the common CAD convention — the text layer carries only the digit; the geometry proved the triangle). The evidence bbox spans digit and triangle",
                "type": "boolean"
              },
              "rev": {
                "type": "string"
              },
              "source": {
                "additionalProperties": false,
                "description": "An evidence pointer — the sheet, the literal text, and where it sits (image px). Every edge in the graph carries one; pass the bbox to view_sheet to LOOK at the source.",
                "properties": {
                  "bbox": {
                    "additionalProperties": false,
                    "properties": {
                      "x0": {
                        "type": "number"
                      },
                      "x1": {
                        "type": "number"
                      },
                      "y0": {
                        "type": "number"
                      },
                      "y1": {
                        "type": "number"
                      }
                    },
                    "required": [
                      "x0",
                      "y0",
                      "x1",
                      "y1"
                    ],
                    "type": "object"
                  },
                  "sheet": {
                    "type": "string"
                  },
                  "text": {
                    "type": "string"
                  }
                },
                "required": [
                  "sheet",
                  "text",
                  "bbox"
                ],
                "type": "object"
              }
            },
            "required": [
              "rev",
              "source"
            ],
            "type": "object"
          },
          "sheet": {
            "type": "string"
          },
          "tag": {
            "type": "string"
          }
        },
        "required": [
          "tag",
          "name",
          "sheet",
          "bbox"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "sheets": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "building": {
            "description": "The sheet's building context, when it names exactly one (BUILDING A / BLDG 2)",
            "type": "string"
          },
          "confidence": {
            "description": "0..1; mixed title signals halve it, a bare sheet-number convention stays under 0.5",
            "type": "number"
          },
          "evidence": {
            "additionalProperties": false,
            "description": "An evidence pointer — the sheet, the literal text, and where it sits (image px). Every edge in the graph carries one; pass the bbox to view_sheet to LOOK at the source.",
            "properties": {
              "bbox": {
                "additionalProperties": false,
                "properties": {
                  "x0": {
                    "type": "number"
                  },
                  "x1": {
                    "type": "number"
                  },
                  "y0": {
                    "type": "number"
                  },
                  "y1": {
                    "type": "number"
                  }
                },
                "required": [
                  "x0",
                  "y0",
                  "x1",
                  "y1"
                ],
                "type": "object"
              },
              "sheet": {
                "type": "string"
              },
              "text": {
                "type": "string"
              }
            },
            "required": [
              "sheet",
              "text",
              "bbox"
            ],
            "type": "object"
          },
          "role": {
            "enum": [
              "plan",
              "schedule",
              "legend",
              "detail",
              "elevation",
              "demolition",
              "unknown"
            ],
            "type": "string"
          },
          "schedules": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "continues": {
                  "description": "Present on a continuation fragment ('… SCHEDULE — CONT'D'): the sheet carrying the table's base fragment. The fragments read as ONE table — resolve_tag and find_schedule already see the union",
                  "type": "string"
                },
                "kind": {
                  "type": "string"
                },
                "region": {
                  "additionalProperties": false,
                  "properties": {
                    "x0": {
                      "type": "number"
                    },
                    "x1": {
                      "type": "number"
                    },
                    "y0": {
                      "type": "number"
                    },
                    "y1": {
                      "type": "number"
                    }
                  },
                  "required": [
                    "x0",
                    "y0",
                    "x1",
                    "y1"
                  ],
                  "type": "object"
                },
                "rotated_headers": {
                  "description": "true when the column headers were read at a quarter-turn",
                  "type": "boolean"
                },
                "rows": {
                  "maximum": 9007199254740991,
                  "minimum": -9007199254740991,
                  "type": "integer"
                },
                "title": {
                  "type": "string"
                }
              },
              "required": [
                "kind",
                "title",
                "rows",
                "region"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "role",
          "confidence",
          "schedules"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "unmatched_tags": {
      "description": "Numbered tags on plan sheets that are NOT counted as rooms — keynote hexagons, detail markers, dimension fragments, legend rows. Listed with a reason, never dropped. A real finish plan is covered in 2–3 digit numbers that are not rooms; counting them as rooms makes every one come back \"no schedule row\", which reads exactly like the lost-bid case and buries it",
      "items": {
        "additionalProperties": false,
        "properties": {
          "bbox": {
            "additionalProperties": false,
            "properties": {
              "x0": {
                "type": "number"
              },
              "x1": {
                "type": "number"
              },
              "y0": {
                "type": "number"
              },
              "y1": {
                "type": "number"
              }
            },
            "required": [
              "x0",
              "y0",
              "x1",
              "y1"
            ],
            "type": "object"
          },
          "building": {
            "type": "string"
          },
          "name": {
            "description": "Text drawn with the number, when there is any — on a keynote legend this is the accessory description, not a room name",
            "type": "string"
          },
          "reason": {
            "description": "WHY this number is not counted as a room. Read these: one of them may be a room the schedule left out, which is a hole in the bid",
            "type": "string"
          },
          "sheet": {
            "type": "string"
          },
          "tag": {
            "type": "string"
          }
        },
        "required": [
          "tag",
          "sheet",
          "bbox",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "available",
    "sheets",
    "rooms",
    "callouts",
    "counts"
  ],
  "type": "object"
}
sha256:929536874b59bf696f6ff20d9e5bb5293aae96f1c8b93a23b706437fad3a726b

Description hash: sha256:f304eeef5bfc2af4890331953e21db9ecb2f0b49b41b9d74b95a0ced43c61910

Interface hash: sha256:b115956976e2554779b25700e578ffa6d6cc5d8868f584e9b7d3e16b8f95f597

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/sheet_graph",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "sheet_graph"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:4b6ecd5cc6b8f60d3be1c829054e200413292cf323ba34506c47a72dc1d007d7"
}
toolunknown0.9.990.9.100
sheet_infokentucky-ai-opentakeoff:tool:sheet_info
Observed interface and hashes

Sheet detail: dims (px and pt), vector segment count, whether the sheet has vector linework (measure_polygon runs on it; get_sheet_vectors returns the strokes), scale status, the detected scale suggestion, and this sheet's committed shape count. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "sheet": {
      "description": "Sheet key (\"plan.pdf\", \"plan.pdf#2\") or title-block number (\"A-101\")",
      "type": "string"
    }
  },
  "required": [
    "sheet"
  ],
  "type": "object"
}
sha256:e9145cecaf83cf1427007c80191c71fb7f21106014234ea5c89a199009690b58

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "detected_scale": {
      "description": "Drawn scale note read off the sheet — a suggestion, never auto-applied",
      "type": "string"
    },
    "has_vector_linework": {
      "description": "one_click needs vector linework",
      "type": "boolean"
    },
    "height_pt": {
      "type": "number"
    },
    "height_px": {
      "type": "number"
    },
    "layers": {
      "description": "The sheet's PDF layer table (#85) — [] when no Optional Content survived export (every engine path then runs the heuristics unchanged)",
      "items": {
        "additionalProperties": false,
        "properties": {
          "confidence": {
            "description": "0..1 — how sure the name classifier is",
            "type": "number"
          },
          "id": {
            "description": "Optional Content Group id — pass to one_click/detect_rooms layers.include/exclude",
            "type": "string"
          },
          "name": {
            "description": "The CAD layer name as exported (e.g. A-WALL-FULL)",
            "type": "string"
          },
          "role": {
            "description": "What this layer's linework IS to a takeoff (lib/layers.ts) — boundary/structure plot hard, pattern/annotation/demolition are excluded, unknown falls back to the hatch heuristics",
            "enum": [
              "boundary",
              "finish-pattern",
              "annotation",
              "structure",
              "demolition",
              "unknown"
            ],
            "type": "string"
          },
          "seg_count": {
            "description": "Segments this layer owns on this sheet",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "visible": {
            "description": "Default-config visibility — a hidden layer's ink is excluded outright (or you trace demolition)",
            "type": "boolean"
          }
        },
        "required": [
          "id",
          "name",
          "role",
          "confidence",
          "visible",
          "seg_count"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "multiple_scales": {
      "const": true,
      "description": "Several DISTINCT scale notes on this sheet (#153) — enlarged plans/details likely",
      "type": "boolean"
    },
    "page": {
      "description": "1-based page number",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "scale_set": {
      "type": "boolean"
    },
    "seg_count": {
      "description": "Vector segment count",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shape_count": {
      "description": "Committed shapes on this sheet",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "sheet": {
      "description": "Sheet key: page 1 is the bare file name (\"plan.pdf\"), pages 2+ are \"plan.pdf#2\"",
      "type": "string"
    },
    "sheet_number": {
      "description": "Title-block sheet number (\"A-101\") where detected",
      "type": "string"
    },
    "upp": {
      "description": "Real feet per image px at render scale 2.0 — present once the scale is set",
      "type": "number"
    },
    "width_pt": {
      "type": "number"
    },
    "width_px": {
      "description": "Image px at render scale 2.0 — the coordinate space every tool speaks",
      "type": "number"
    }
  },
  "required": [
    "sheet",
    "page",
    "width_pt",
    "height_pt",
    "width_px",
    "height_px",
    "seg_count",
    "has_vector_linework",
    "scale_set",
    "shape_count",
    "layers"
  ],
  "type": "object"
}
sha256:0a948126573d842729299e077e03f876fa606f3f1f9d4f15b250ef952068119e

Description hash: sha256:4cf3c915379c848805a53a431cb5aab2e5edfc613b7f1888642f44e506531e9d

Interface hash: sha256:b634714e2a691fbcebde6ba0807255c121b8787a9803522535da3f74e2a26b94

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/sheet_info",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "sheet_info"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:f8ae1dcc200b13bc1c9764a3650f720a070c9edc6d2e31c27c8e43ec34ff63e3"
}
toolread0.9.990.9.100
split_conditionkentucky-ai-opentakeoff:tool:split_condition
Observed interface and hashes

Cut a twin loose from its family: every following material row freezes at its current values and edits to the original stop reaching it. It keeps its finish tag and still groups with its siblings — only the inheritance ends. Use when two variants have diverged far enough that following one another is wrong. A condition that already owns its materials returns split:false rather than erroring. Reversible with undo_last.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "condition": {
      "description": "Finish tag of the twin to split, e.g. 'CPT-1 – Level 2'",
      "type": "string"
    }
  },
  "required": [
    "condition"
  ],
  "type": "object"
}
sha256:9359d9e67ed2eb22cdf46e56f14e8dabf8603ce5325aa15b8cce5c498ff1621e

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "condition": {
      "type": "string"
    },
    "condition_id": {
      "type": "string"
    },
    "family_id": {
      "description": "Kept — it still groups with its siblings",
      "type": "string"
    },
    "frozen_rows": {
      "description": "Following rows frozen at their current values",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "note": {
      "type": "string"
    },
    "split": {
      "description": "false = it already owned its materials; nothing was following",
      "type": "boolean"
    }
  },
  "required": [
    "condition",
    "condition_id",
    "split",
    "frozen_rows",
    "note"
  ],
  "type": "object"
}
sha256:d1b2ae0be2bc681f7097e3a453c89a69a8a88385ea2791c68ce4d44a9695bb0f

Description hash: sha256:cd844a0b2532d3ff9cba0a0677bb12b2b3b731dd179ca7013773e5a2d3c84495

Interface hash: sha256:7baa30c1bafa47c3681c9c99fdd1fec6c90b552b2ec4445b71030022096280c3

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/split_condition",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "split_condition"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:bbdae6a6585476f34f0a40e9ce4e3924d7e9053c936c33d36d38ba3d8dc4c93e"
}
toolunknown0.9.990.9.100
sweep_schedule_rowkentucky-ai-opentakeoff:tool:sweep_schedule_row
Observed interface and hashes

Take off a schedule row's mark from the row itself — the estimator's own gesture: a transition type sometimes exists only as a schedule row plus tag markers scattered across the plan sheets, and this tool mints the condition FROM the row and finds every occurrence. Pass the row's key (e.g. 'T1') and the tool (1) reads the row from the set's schedule tables (the sheet_graph/find_schedule machinery — the row is the condition's cited source), (2) anchors a geometric fingerprint on the marker the tag is DRAWN as on a plan sheet (a deterministic pad ladder around the tag text; where the tag occurs more than once the fingerprint must recur at a second occurrence before it is trusted — `anchor.corroborated`), and (3) sweeps every PLAN-role sheet for it. The count is geometry AND text agreeing: drafting reuses one bubble shape across many marks, so a match counts ONLY when the row's own tag sits within the marker footprint (its bbox rides the match as `tag_at` evidence); a match labeled with a SIBLING row's tag is excluded and says whose it is, an unlabeled match is withheld as a question, and a tag drawn with no matching marker is disclosed as text_only. REFUSAL over guessing, with the reason and the fix: no such row; the same key in two tables (ambiguous); a tag drawn on no plan sheet; no repeatable marker linework around the tag — a fingerprint is never guessed from text alone (the fallback is always: marquee one instance with symbol_sweep). commit: true commits the counted matches as EA markers under the row's own key — one undo step for the whole set-wide sweep, every marker carrying origin.assignment {source: "schedule"} plus the anchor and row citation on origin.symbol.seed. The COUNT is scale-free (EA), but matching is not: where the anchor sheet and a target sheet both carry a scale, the marker is resized by their exact ratio before matching (`scaled` per sheet), and where one does not, the sweep runs at 1:1 and discloses it (`scale_assumed`) rather than reporting a confident zero. After committing, LOOK: view_sheet {overlay: true} over each swept sheet. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt. LABEL-FIRST for devices (any trade): when the marker cannot be fingerprinted or does not reach a drawn tag amid linework — a heater bar or fan drawn to its own size, tagged by a leader — every such tag on a plan sheet counts as ONE instance BY LABEL, disclosed in found_by_label / label_only / counted_by; a bare mention in a note (no linework near it) is text_only, never a count. Rows come from every schedule family the sheet graph reads: room-finish, finish/material, and equipment (mechanical, electrical, plumbing, fire).

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "commit": {
      "default": false,
      "description": "Commit every counted match as one EA count marker (excluded/withheld/text_only never commit)",
      "type": "boolean"
    },
    "mirror": {
      "default": true,
      "description": "Also match mirrored markers",
      "type": "boolean"
    },
    "rotations": {
      "default": true,
      "description": "Also match 90/180/270-rotated markers",
      "type": "boolean"
    },
    "tag": {
      "description": "The schedule row's key exactly as drawn, e.g. 'T1', 'TR-2' — it becomes the condition tag on commit",
      "minLength": 1,
      "type": "string"
    },
    "tolerance_px": {
      "default": 2,
      "description": "Endpoint match tolerance in image px (default 2 — CAD jitter, not drift)",
      "exclusiveMinimum": 0,
      "maximum": 20,
      "type": "number"
    }
  },
  "required": [
    "tag"
  ],
  "type": "object"
}
sha256:4bc66ff3e8863072f11ff6b83816ef9aa72531d0bc7ad4e101dd9db1dd5cb48d

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "anchor": {
      "anyOf": [
        {
          "additionalProperties": false,
          "properties": {
            "at": {
              "additionalItems": false,
              "description": "The anchoring tag occurrence's center (image px)",
              "items": [
                {
                  "type": "number"
                },
                {
                  "type": "number"
                }
              ],
              "maxItems": 2,
              "minItems": 2,
              "type": "array"
            },
            "corroborated": {
              "description": "true = the fingerprint recurred at a second tag occurrence before being trusted; false = the tag is drawn too sparsely to cross-check (see note)",
              "type": "boolean"
            },
            "length_px": {
              "type": "number"
            },
            "occurrences": {
              "description": "Drawn occurrences of the tag across all plan sheets",
              "maximum": 9007199254740991,
              "minimum": -9007199254740991,
              "type": "integer"
            },
            "rect": {
              "description": "The fingerprint rect actually used [x0, y0, x1, y1] — the pad ladder's winning step",
              "items": {
                "type": "number"
              },
              "maxItems": 4,
              "minItems": 4,
              "type": "array"
            },
            "segments": {
              "description": "Vector segments in the marker fingerprint",
              "maximum": 9007199254740991,
              "minimum": -9007199254740991,
              "type": "integer"
            },
            "sheet": {
              "description": "The plan sheet the fingerprint was anchored on",
              "type": "string"
            }
          },
          "required": [
            "sheet",
            "at",
            "rect",
            "segments",
            "length_px",
            "corroborated",
            "occurrences"
          ],
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "description": "null when the sweep counted BY LABEL: no repeatable marker geometry sits around the drawn tag (the equipment convention — a device drawn to its own size, tagged by a leader), so nothing was fingerprinted"
    },
    "committed": {
      "description": "commit mode: count shapes committed — one per counted match, the whole sweep ONE undo step",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "complete": {
      "description": "True when every proposed placement was scored on every swept sheet — false means at least one sheet's count is a FLOOR, not a total (#261)",
      "type": "boolean"
    },
    "condition": {
      "description": "commit mode: the condition minted FROM the row — its key is the tag",
      "type": "string"
    },
    "counted_by": {
      "description": "How the count was made — \"label\" means no marker geometry was matched at all; look at each label_only placement before pricing",
      "enum": [
        "geometry",
        "label",
        "mixed"
      ],
      "type": "string"
    },
    "ea_total": {
      "type": "number"
    },
    "found": {
      "description": "Instances counted across every plan sheet: geometry matches carrying the row's own tag PLUS drawn tags counted by label — see counted_by",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "found_by_geometry": {
      "description": "…of which marker-fingerprint matches corroborated by the tag",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "found_by_label": {
      "description": "…of which drawn tags amid linework the fingerprint did not (or could not) reach — an installed instance by the equipment convention, disclosed as label-counted",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "note": {
      "type": "string"
    },
    "row": {
      "additionalProperties": false,
      "description": "The schedule row the sweep was seeded from — the condition's source",
      "properties": {
        "cells": {
          "additionalProperties": {
            "type": "string"
          },
          "description": "The row's cells, header → text — what the schedule SAYS this mark is",
          "propertyNames": {
            "type": "string"
          },
          "type": "object"
        },
        "citation": {
          "additionalProperties": false,
          "description": "An evidence pointer — the sheet, the literal text, and where it sits (image px). Every edge in the graph carries one; pass the bbox to view_sheet to LOOK at the source.",
          "properties": {
            "bbox": {
              "additionalProperties": false,
              "properties": {
                "x0": {
                  "type": "number"
                },
                "x1": {
                  "type": "number"
                },
                "y0": {
                  "type": "number"
                },
                "y1": {
                  "type": "number"
                }
              },
              "required": [
                "x0",
                "y0",
                "x1",
                "y1"
              ],
              "type": "object"
            },
            "sheet": {
              "type": "string"
            },
            "text": {
              "type": "string"
            }
          },
          "required": [
            "sheet",
            "text",
            "bbox"
          ],
          "type": "object"
        },
        "key": {
          "type": "string"
        },
        "sheet": {
          "type": "string"
        },
        "table": {
          "description": "The table's title (or kind, when untitled)",
          "type": "string"
        }
      },
      "required": [
        "sheet",
        "table",
        "key",
        "cells",
        "citation"
      ],
      "type": "object"
    },
    "shape_ids": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "sheets": {
      "description": "One entry per swept PLAN-role sheet, load order",
      "items": {
        "additionalProperties": false,
        "properties": {
          "candidates": {
            "additionalProperties": false,
            "properties": {
              "considered": {
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "dropped": {
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              }
            },
            "required": [
              "considered",
              "dropped"
            ],
            "type": "object"
          },
          "complete": {
            "description": "True when every proposed placement on this sheet was scored — false means this sheet's count is a FLOOR, not a total (#261)",
            "type": "boolean"
          },
          "elapsed_ms": {
            "description": "Wall-clock for this sheet's sweep",
            "type": "number"
          },
          "excluded": {
            "description": "Markers matching the geometry but labeled with a SIBLING row's tag — the bubble shape is shared across marks, so these belong to that row, not this one",
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "tag": {
                  "type": "string"
                }
              },
              "required": [
                "at",
                "tag"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "found": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "label_only": {
            "description": "Instances counted BY LABEL: the row's tag drawn amid linework that the marker fingerprint did not match (or none was anchored) — the equipment convention; each is counted and each deserves a look",
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "tag_at": {
                  "additionalProperties": false,
                  "properties": {
                    "x0": {
                      "type": "number"
                    },
                    "x1": {
                      "type": "number"
                    },
                    "y0": {
                      "type": "number"
                    },
                    "y1": {
                      "type": "number"
                    }
                  },
                  "required": [
                    "x0",
                    "y0",
                    "x1",
                    "y1"
                  ],
                  "type": "object"
                }
              },
              "required": [
                "at",
                "tag_at"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "matches": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "description": "The matched marker's centroid (image px)",
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "mirrored": {
                  "type": "boolean"
                },
                "rotation": {
                  "description": "Detected rotation in degrees (0 | 90 | 180 | 270)",
                  "type": "number"
                },
                "score": {
                  "description": "Length-weighted fraction of the anchor's segments matched within tolerance, 0..1",
                  "type": "number"
                },
                "tag_at": {
                  "additionalProperties": false,
                  "description": "The corroborating tag text's bbox — the evidence that this marker is THIS row's",
                  "properties": {
                    "x0": {
                      "type": "number"
                    },
                    "x1": {
                      "type": "number"
                    },
                    "y0": {
                      "type": "number"
                    },
                    "y1": {
                      "type": "number"
                    }
                  },
                  "required": [
                    "x0",
                    "y0",
                    "x1",
                    "y1"
                  ],
                  "type": "object"
                }
              },
              "required": [
                "at",
                "score",
                "rotation",
                "mirrored",
                "tag_at"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "scale_assumed": {
            "description": "#186: present when the true ratio is UNKNOWN (a scale is missing on the seed sheet or this one) and the sweep ran at 1:1 — an unstated ratio plus a zero count is not evidence of absence",
            "type": "string"
          },
          "scaled": {
            "additionalProperties": false,
            "description": "#186: present only when the seed was resized for this sheet",
            "properties": {
              "footprint_px": {
                "description": "The symbol's size on THIS sheet after the resize",
                "type": "number"
              },
              "ratio": {
                "description": "Seed-sheet px per target-sheet px, computed from the two sheets' own committed scales (upp_seed / upp_target) — stated, never scale-searched",
                "type": "number"
              },
              "segments": {
                "description": "Fingerprint segments that survived the resize and were actually searched for",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "sub_pixel_dropped": {
                "description": "Seed segments that fell below matchable length when scaled down — excluded from the score rather than depressing it, so a score here is a fraction of what survived, not of the whole seed",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "tol_px": {
                "description": "The endpoint tolerance actually applied — it rides the ratio up when the seed is magnified (its drawn jitter magnifies too) and never down",
                "type": "number"
              }
            },
            "required": [
              "ratio",
              "segments",
              "sub_pixel_dropped",
              "footprint_px",
              "tol_px"
            ],
            "type": "object"
          },
          "sheet": {
            "type": "string"
          },
          "text_only": {
            "description": "The tag drawn with no marker match AND no linework near it — a note mentioning the mark; a question, never a count",
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                }
              },
              "required": [
                "at"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "withheld": {
            "description": "Questions, never counts: markers matching the geometry but carrying no tag (an unlabeled instance or a shared bubble shape), and near-miss scores in the [0.75, 0.92) band",
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "description": "The matched marker's centroid (image px)",
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "mirrored": {
                  "type": "boolean"
                },
                "reason": {
                  "type": "string"
                },
                "rotation": {
                  "description": "Detected rotation in degrees (0 | 90 | 180 | 270)",
                  "type": "number"
                },
                "score": {
                  "description": "Length-weighted fraction of the anchor's segments matched within tolerance, 0..1",
                  "type": "number"
                }
              },
              "required": [
                "at",
                "score",
                "rotation",
                "mirrored",
                "reason"
              ],
              "type": "object"
            },
            "type": "array"
          }
        },
        "required": [
          "sheet",
          "found",
          "matches",
          "withheld",
          "excluded",
          "text_only",
          "label_only",
          "candidates",
          "complete",
          "elapsed_ms"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "skipped": {
      "description": "Sheets excluded from counting (schedule/detail/legend/unknown), each with its reason",
      "items": {
        "additionalProperties": false,
        "properties": {
          "reason": {
            "type": "string"
          },
          "role": {
            "type": "string"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "role",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "tag": {
      "description": "The row key as normalized (the tag as drawn)",
      "type": "string"
    },
    "warning": {
      "description": "Present when the per-sheet work cap dropped candidates",
      "type": "string"
    }
  },
  "required": [
    "tag",
    "row",
    "anchor",
    "found",
    "found_by_geometry",
    "found_by_label",
    "counted_by",
    "sheets",
    "complete",
    "skipped"
  ],
  "type": "object"
}
sha256:aa2b22dc7fd06c9e88aa83026faccc7820dd9d39152c9c97a9294fba77ea2000

Description hash: sha256:eb2e8d520e24a91805a69c3f0843d3a5fd3e112c91a6a765f148cfbdef57d52c

Interface hash: sha256:b7ccfbd2f3a36080543e9fcb571c213ee12dab9e2cb74f72170c62ee7d9326fc

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/sweep_schedule_row",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "sweep_schedule_row"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:010952086fa63368b71b18aa0d783ea2b60022214e1ea0ece7b1e148b59c178e"
}
toolwrite0.9.990.9.100
symbol_sweepkentucky-ai-opentakeoff:tool:symbol_sweep
Observed interface and hashes

Find EVERY instance of a repeated plan symbol from ONE example — drains, thresholds, fixtures, transition markers: marquee a tight seed_rect around a single instance and the vector linework is searched for every other placement of that same segment cluster. Deterministic geometry, not vision: each placement scores as the length-weighted fraction of the seed's segments reproduced within tolerance_px, under translation plus 0/90/180/270 rotation and mirroring (symbols rotate on plans — both ON by default; turn them off to pin orientation). Score ≥ 0.92 is a match; the 0.75–0.92 band comes back in `withheld` with a reason — a near-match is a question you answer by LOOKING (view_sheet at its `at`), never a silent commit and never a silent drop. RICHER VARIANTS are named, never silent: a placement that reproduces the whole seed but carries >30% extra linework fully inside its footprint (a register against a grille seed — the same outline plus louvers) comes back with its measured `extra` fraction on the row — LOOK at those first, they are the classic mislabel; background lines CROSSING the symbol and coincident duplicate ink never trip this. By default such placements still COUNT, because the contained-seed workflow below depends on supersets matching (seed a bare sub-shape, count the richer symbols that contain it, exclude what you don't mean). Pass `variant_guard: true` when your seed is the WHOLE symbol — grilles, drains, fixtures marqueed complete — and extra-ink placements demote to `withheld` as questions instead of counting; the guard stands down automatically when `exclude` counter-examples are in play, since supplying negatives is manual variant discrimination. The seed's own location is reported in `seed` and never double-committed. Every proposed placement is scored up to a hard work ceiling sized for pathological sheets, and the reply says which it was: complete true means the count is a total; complete false (with candidates.dropped > 0) means the count is a FLOOR — some placements were never scored — so tighten the seed rect around more distinctive geometry rather than trusting it as a total. Marquee discipline: the rect must hug ONE instance — only segments FULLY inside it define the symbol, so a loose rect that swallows wall linework fingerprints the wall, not the symbol. scope "set" sweeps the WHOLE working set, counting on PLAN-role sheets only (the sheet graph decides): a symbol drawn in a detail, legend, or schedule is a reference drawing and never counts itself — which is also how you seed from one: marquee the assembly on the detail sheet and its plan-sheet occurrences are counted while the detail stays excluded (the exclusion disclosed in `skipped`, per-sheet results with per-sheet caps and wall-clock in `sheets`). Scale across sheets: the fingerprint is size-true and is never scale-SEARCHED, so a detail drawn at 1-1/2" = 1'-0" is 12× the size of the same mark on a 1/8" plan — when BOTH sheets have a scale set, the exact ratio is computed from them and the seed is resized before matching (reported per sheet as `scaled`); when a scale is missing, the sweep runs at 1:1 and SAYS so (`scale_assumed`), because an unknown ratio plus a zero count is not evidence of absence. Seeding from a detail/legend/schedule sheet REFUSES outright until both scales are set — that is the case where an unstated ratio silently finds nothing. commit: true (requires condition) commits every match center as an EA count marker through the same path as place_count — the whole sweep (set-wide included) is ONE undo step, each marker carries origin.method "symbol_sweep" with its score, transform, and seed source, and withheld placements are NEVER committed. The SEED instance is not in that count (#296) — in sheet scope it is almost always installed work, so pass commit_seed: true to mint it into the same batch (the reply reminds you whenever a sheet-scope commit leaves it out; ea_total one short of the hand tally is exactly this). The COUNT is scale-free (EA), but matching across sheets of different scales is not — set_scale on the sheets involved is what turns the ratio from an assumption into arithmetic. Counter-examples (#259): drafting reuses one generic shape for different devices — a wall-mounted data outlet drawn as a plain triangle, the flush-floor variant the SAME triangle inside a square, keynote callouts a triangle with a letter in it — so the seed legitimately matches things you do not mean, and seeding more geometry only works where the drawing offers more to capture. `exclude` takes rects around instances you do NOT mean, marqueed exactly like the seed. You never choose a mechanism; the rect's contents decide, because both are the same gesture: a rect holding EXTRA linework beyond the seed rejects placements where that extra linework is present too (the box, the letter), and a rect holding no extra linework of its own is read as the line running THROUGH it — a bare ceiling-grid tile whose grid line a real fixture, drawn over it, would BREAK. That second mechanic is not expressible as a seed: only segments fully INSIDE a rect define a symbol, and background structure is long by nature. Every rejection is disclosed in rejected[] — which negative, what fraction of its evidence was found, and the placement — and NEVER counted in found: an exclusion is a judgement, so look at it and reinstate any you disagree with using place_count at its `at`. A counter-example that holds no instance of the seed, or holds the seed with nothing extra, is REFUSED rather than silently doing nothing. Stroke luminance (#260): a flattened export strips the layer tree and flattens every pen, but the file still STATES stroke color — a black fixture outline over a grey ceiling grid is unambiguous there even when the geometry is identical (two empty 2 ft grid tiles reproduce a 2×4 fixture's outline exactly). luminance_tolerance (0–254) gates on it: a sheet segment only answers for a seed segment when their stroke luminances are within the stated tolerance (Rec. 709, 0 = black, 255 = white; 32–64 separates black from grey without touching anti-aliasing wobble). OPT-IN and disclosed, in the spirit of tolerance_px — omitted, sweeps score exactly as before; stated, the reply's lum_gate says the seed's own luminance band and names every placement the geometry would have committed and the pen did not, so you can LOOK at what a stated gate cost. Prefer geometry (a counter-example, a tighter seed) where the drawing offers it — color is the fallback for exports where nothing else survived. Labels (#308): for a LABELED family — fixtures, tagged equipment, keyed devices — the drawing already names every instance, and the sweep reads those names: a fixture token written beside a placement, or connected to it by a drawn leader line (leader-following arms only on multi-pen sheets, where the annotation pen separates from the work), comes back as `label` + `label_via` on the row, and the seed's own tag rides `seed.label`. Disclosure in both directions, never a recount: a committed match with NO label while the family is labeled was counted on shape alone (measured case: two 0.97 matches that were valve internals, not drains — LOOK at those first), a withheld row carrying the seed's own tag is the drawing vouching for a near-miss (look, then place_count), and a withheld row named a DIFFERENT tag is a sibling fixture answered, not a missed count. After any batch commit, LOOK at what landed — view_sheet {overlay: true} over the swept area — and audit the markers against the drawing before trusting the EA total. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "commit": {
      "default": false,
      "description": "Commit every MATCH center as one EA count marker (withheld placements never commit)",
      "type": "boolean"
    },
    "commit_seed": {
      "default": false,
      "description": "Sheet scope + commit only (#296): also commit the SEED instance — in sheet scope the seed is almost always installed work, and a count that excludes it bids one short. Joins the same one-undo-step batch, origin score 1. Refused in set scope, where a detail/legend seed is a reference drawing",
      "type": "boolean"
    },
    "condition": {
      "description": "Finish tag to commit match markers under (minted on first use), e.g. 'FD-1'. Required when commit is true",
      "type": "string"
    },
    "exclude": {
      "description": "Counter-examples: rects around instances you do NOT mean, same gesture as seed_rect — 'count the triangles, not the keynote ones'. Marquee the LOOKALIKE ITSELF (the flush-floor variant with its box, the keynote triangle with its letter) or an EMPTY position whose background line a real instance would break (a bare ceiling grid tile). You never say which kind it is: the rect's own contents decide. Every rejection comes back in rejected[] with which negative did it and what it saw",
      "items": {
        "additionalItems": false,
        "items": [
          {
            "additionalItems": false,
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          {
            "additionalItems": false,
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          }
        ],
        "maxItems": 2,
        "minItems": 2,
        "type": "array"
      },
      "type": "array"
    },
    "luminance_tolerance": {
      "description": "Stroke-luminance gate, 0–254 (#260): a sheet segment only answers for a seed segment when their stroke luminances (Rec. 709, 0 black – 255 white) are within this. For flattened exports where a black device and its grey background twin are geometrically identical — 32–64 separates black from grey. Omit to score on geometry alone; stated, the reply's lum_gate discloses the seed's luminance band and every placement the gate pulled under the commit bar",
      "maximum": 254,
      "minimum": 0,
      "type": "integer"
    },
    "mirror": {
      "default": true,
      "description": "Also match mirrored placements",
      "type": "boolean"
    },
    "rotations": {
      "default": true,
      "description": "Also match 90/180/270-rotated placements",
      "type": "boolean"
    },
    "scope": {
      "default": "sheet",
      "description": "\"sheet\" = this sheet only; \"set\" = every PLAN-role sheet in the working set (needs a text layer for the sheet graph; non-plan sheets are excluded and disclosed)",
      "enum": [
        "sheet",
        "set"
      ],
      "type": "string"
    },
    "seed_rect": {
      "additionalItems": false,
      "description": "Marquee around ONE example instance, [[x0,y0],[x1,y1]] in image px — tight: segments fully inside define the symbol",
      "items": [
        {
          "additionalItems": false,
          "items": [
            {
              "type": "number"
            },
            {
              "type": "number"
            }
          ],
          "maxItems": 2,
          "minItems": 2,
          "type": "array"
        },
        {
          "additionalItems": false,
          "items": [
            {
              "type": "number"
            },
            {
              "type": "number"
            }
          ],
          "maxItems": 2,
          "minItems": 2,
          "type": "array"
        }
      ],
      "maxItems": 2,
      "minItems": 2,
      "type": "array"
    },
    "sheet": {
      "description": "The sheet the seed rect sits on — in scope 'set' it may be ANY sheet (a detail/legend seed sheet is fingerprint source only, never counted)",
      "type": "string"
    },
    "tolerance_px": {
      "default": 2,
      "description": "Endpoint match tolerance in image px (default 2 — CAD jitter, not drift)",
      "exclusiveMinimum": 0,
      "maximum": 20,
      "type": "number"
    },
    "variant_guard": {
      "default": false,
      "description": "Whole-symbol mode: demote richer-variant placements (>30% extra linework inside the footprint) to withheld instead of counting them with an `extra` disclosure. Use when the seed is a COMPLETE symbol (a grille, a drain); leave off when seeding a contained sub-shape. Stands down when exclude counter-examples are passed",
      "type": "boolean"
    }
  },
  "required": [
    "sheet",
    "seed_rect"
  ],
  "type": "object"
}
sha256:284ca1fc17499f34f807f8c6ba8e5a63fcedce6dd44509337e886ab9223cb6f8

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "candidates": {
      "additionalProperties": false,
      "description": "Sheet scope only — set scope accounts per sheet in sheets[]",
      "properties": {
        "considered": {
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "dropped": {
          "description": "Placements never scored because the work cap bit — always disclosed, never silent",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        }
      },
      "required": [
        "considered",
        "dropped"
      ],
      "type": "object"
    },
    "commit_refused": {
      "description": "commit mode (#376): present when the seed was too small and too common to commit on shape alone — fewer than 40 segments of seed linework and more than 50 placements cleared the bar. NOTHING was committed; the placements are still listed in matches (or per sheet in sheets[]) so you can look, and the text says what stands the guard down: variant_guard: true, exclude counter-examples, or a seed rect that captures more of the symbol",
      "type": "string"
    },
    "committed": {
      "description": "commit mode: count shapes committed — one per match (0 when commit_refused is present)",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "complete": {
      "description": "True when every proposed placement was scored (every swept sheet, in set scope) and the count is a total. FALSE MEANS THE COUNT IS A FLOOR — acknowledge it before trusting found (#261)",
      "type": "boolean"
    },
    "condition": {
      "description": "commit mode: the finish tag the markers counted under",
      "type": "string"
    },
    "ea_total": {
      "description": "commit mode: the condition's total EA after this call",
      "type": "number"
    },
    "found": {
      "description": "Placements that cleared the commit bar — across every swept sheet in set scope",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "lum_gate": {
      "additionalProperties": false,
      "description": "Sheet scope only. The stated stroke-luminance gate's accounting (#260): the tolerance, the seed's own luminance band, and every placement the geometry would have committed that the pen pulled under the bar — NEVER counted in found, never silent. Set scope accounts per sheet in sheets[]",
      "properties": {
        "at": {
          "description": "Where each of them is, image px — view_sheet and look before trusting the gate; place_count reinstates one you disagree with",
          "items": {
            "additionalItems": false,
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "type": "array"
        },
        "rejected": {
          "description": "Placements the geometry alone would have COMMITTED and the gate did not — one entry per physical spot",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "seed_lum": {
          "description": "The seed's own stroke luminances, deduplicated — the band candidates were held to",
          "items": {
            "type": "number"
          },
          "type": "array"
        },
        "tol": {
          "description": "The luminance tolerance that was applied, 0–254",
          "type": "number"
        }
      },
      "required": [
        "tol",
        "seed_lum",
        "rejected",
        "at"
      ],
      "type": "object"
    },
    "matches": {
      "description": "Sheet scope only. Deterministic reading order (y, then x). The seed's own location is never listed here",
      "items": {
        "additionalProperties": false,
        "properties": {
          "at": {
            "additionalItems": false,
            "description": "The placed symbol's centroid (image px) — the point a commit places its count marker at",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "extra": {
            "description": "Richer-variant disclosure: the fraction of the seed's total length found as UNMATCHED extra linework fully inside this placement's footprint, present when past the 0.30 bar — the classic grille-counted-as-register shape; LOOK at these first. Under variant_guard such placements demote to withheld instead of matching",
            "type": "number"
          },
          "label": {
            "description": "The drawing's own tag for this placement (#308) — a fixture token written beside it or connected by a drawn leader (e.g. \"P-7\", \"FD1\"). Disclosure, never a recount: a match with NO label in a labeled family was counted on shape alone (look before trusting), and a withheld row carrying the seed's own tag is the drawing vouching for it",
            "type": "string"
          },
          "label_via": {
            "description": "How the tag reached this placement: written beside it, or followed along a drawn leader line (leader-following arms only on multi-pen sheets, where the annotation pen separates from the work)",
            "enum": [
              "adjacent",
              "leader"
            ],
            "type": "string"
          },
          "mirrored": {
            "type": "boolean"
          },
          "rotation": {
            "description": "Detected rotation in degrees (0 | 90 | 180 | 270)",
            "type": "number"
          },
          "score": {
            "description": "Length-weighted fraction of the seed's segments matched within tolerance, 0..1",
            "type": "number"
          }
        },
        "required": [
          "at",
          "score",
          "rotation",
          "mirrored"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "negatives": {
      "description": "What each `exclude` rect was read as, in the order you passed them (#259)",
      "items": {
        "additionalProperties": false,
        "properties": {
          "center": {
            "additionalItems": false,
            "description": "Where the seed's own geometry was located inside that rect, image px — what the negative aligned to",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "mode": {
            "enum": [
              "shape",
              "crossing"
            ],
            "type": "string"
          },
          "segments": {
            "description": "Discriminating segments this counter-example contributes — the linework that is NOT the seed",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          }
        },
        "required": [
          "mode",
          "segments",
          "center"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "note": {
      "type": "string"
    },
    "rejected": {
      "description": "Sheet scope only. Placements the geometry accepted and a counter-example refused (#259) — NEVER counted in found, and never silent: each says which negative did it and what it saw. Reinstate one by hand with place_count at its `at` if you disagree",
      "items": {
        "additionalProperties": false,
        "properties": {
          "at": {
            "additionalItems": false,
            "description": "The placed symbol's centroid (image px) — the point a commit places its count marker at",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "by": {
            "description": "Which counter-example rejected it — 1-based index into the `exclude` rects you passed",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "evidence": {
            "description": "Fraction of that counter-example's discriminating linework found at this placement, 0..1 (rejection bar 0.5)",
            "type": "number"
          },
          "extra": {
            "description": "Richer-variant disclosure: the fraction of the seed's total length found as UNMATCHED extra linework fully inside this placement's footprint, present when past the 0.30 bar — the classic grille-counted-as-register shape; LOOK at these first. Under variant_guard such placements demote to withheld instead of matching",
            "type": "number"
          },
          "label": {
            "description": "The drawing's own tag for this placement (#308) — a fixture token written beside it or connected by a drawn leader (e.g. \"P-7\", \"FD1\"). Disclosure, never a recount: a match with NO label in a labeled family was counted on shape alone (look before trusting), and a withheld row carrying the seed's own tag is the drawing vouching for it",
            "type": "string"
          },
          "label_via": {
            "description": "How the tag reached this placement: written beside it, or followed along a drawn leader line (leader-following arms only on multi-pen sheets, where the annotation pen separates from the work)",
            "enum": [
              "adjacent",
              "leader"
            ],
            "type": "string"
          },
          "mirrored": {
            "type": "boolean"
          },
          "mode": {
            "description": "What that counter-example was read as. \"shape\": it carries extra linework the seed does not, and that linework is present here too. \"crossing\": it carries no extra linework of its own — what marks it is a line running THROUGH it, and that line runs unbroken through this placement",
            "enum": [
              "shape",
              "crossing"
            ],
            "type": "string"
          },
          "reason": {
            "type": "string"
          },
          "rotation": {
            "description": "Detected rotation in degrees (0 | 90 | 180 | 270)",
            "type": "number"
          },
          "score": {
            "description": "Length-weighted fraction of the seed's segments matched within tolerance, 0..1",
            "type": "number"
          }
        },
        "required": [
          "at",
          "score",
          "rotation",
          "mirrored",
          "by",
          "mode",
          "evidence",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "rejected_total": {
      "description": "Set scope: placements counter-examples rejected across every swept sheet",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "scope": {
      "description": "\"sheet\" = the swept sheet alone (matches/withheld/candidates at top level); \"set\" = every PLAN-role sheet in the working set (per-sheet results in sheets[], exclusions in skipped[])",
      "enum": [
        "sheet",
        "set"
      ],
      "type": "string"
    },
    "seed": {
      "additionalProperties": false,
      "properties": {
        "center": {
          "additionalItems": false,
          "description": "The seed instance's own centroid (image px) — reported here, never double-committed as a match",
          "items": [
            {
              "type": "number"
            },
            {
              "type": "number"
            }
          ],
          "maxItems": 2,
          "minItems": 2,
          "type": "array"
        },
        "label": {
          "description": "The drawing's own tag for the seed instance (#308) — the family's identity, e.g. seeding a drain the sheet labels \"P-7\"",
          "type": "string"
        },
        "label_via": {
          "enum": [
            "adjacent",
            "leader"
          ],
          "type": "string"
        },
        "length_px": {
          "description": "Total seed linework length, image px",
          "type": "number"
        },
        "rect": {
          "description": "The seed rect actually used, post-clamp [x0, y0, x1, y1]",
          "items": {
            "type": "number"
          },
          "maxItems": 4,
          "minItems": 4,
          "type": "array"
        },
        "role": {
          "description": "Set scope: the seed sheet's graph role — a non-plan seed sheet is the fingerprint SOURCE and is excluded from counting",
          "type": "string"
        },
        "segments": {
          "description": "Vector segments fully inside the seed rect — the fingerprint",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991,
          "type": "integer"
        },
        "sheet": {
          "description": "The sheet the seed rect was marqueed on",
          "type": "string"
        }
      },
      "required": [
        "sheet",
        "segments",
        "center",
        "rect",
        "length_px"
      ],
      "type": "object"
    },
    "seed_committed": {
      "description": "Present when commit_seed: true minted the seed instance into the batch (#296) — ea_total then includes it",
      "type": "boolean"
    },
    "shape_ids": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "sheets": {
      "description": "Set scope only: one entry per swept PLAN-role sheet, load order",
      "items": {
        "additionalProperties": false,
        "properties": {
          "candidates": {
            "additionalProperties": false,
            "description": "The work ceiling applies PER SHEET; dropped > 0 here names exactly where the count is incomplete",
            "properties": {
              "considered": {
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "dropped": {
                "description": "Placements never scored because the work cap bit — always disclosed, never silent",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              }
            },
            "required": [
              "considered",
              "dropped"
            ],
            "type": "object"
          },
          "complete": {
            "description": "True when every proposed placement on this sheet was scored — false means this sheet's count is a FLOOR, not a total (#261)",
            "type": "boolean"
          },
          "elapsed_ms": {
            "description": "Wall-clock for this sheet's sweep",
            "type": "number"
          },
          "found": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "lum_gate": {
            "additionalProperties": false,
            "description": "This sheet's stated-luminance-gate accounting (#260) — present only when luminance_tolerance was stated",
            "properties": {
              "at": {
                "description": "Where each of them is, image px — view_sheet and look before trusting the gate; place_count reinstates one you disagree with",
                "items": {
                  "additionalItems": false,
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "type": "array"
              },
              "rejected": {
                "description": "Placements the geometry alone would have COMMITTED and the gate did not — one entry per physical spot",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "seed_lum": {
                "description": "The seed's own stroke luminances, deduplicated — the band candidates were held to",
                "items": {
                  "type": "number"
                },
                "type": "array"
              },
              "tol": {
                "description": "The luminance tolerance that was applied, 0–254",
                "type": "number"
              }
            },
            "required": [
              "tol",
              "seed_lum",
              "rejected",
              "at"
            ],
            "type": "object"
          },
          "matches": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "description": "The placed symbol's centroid (image px) — the point a commit places its count marker at",
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "extra": {
                  "description": "Richer-variant disclosure: the fraction of the seed's total length found as UNMATCHED extra linework fully inside this placement's footprint, present when past the 0.30 bar — the classic grille-counted-as-register shape; LOOK at these first. Under variant_guard such placements demote to withheld instead of matching",
                  "type": "number"
                },
                "label": {
                  "description": "The drawing's own tag for this placement (#308) — a fixture token written beside it or connected by a drawn leader (e.g. \"P-7\", \"FD1\"). Disclosure, never a recount: a match with NO label in a labeled family was counted on shape alone (look before trusting), and a withheld row carrying the seed's own tag is the drawing vouching for it",
                  "type": "string"
                },
                "label_via": {
                  "description": "How the tag reached this placement: written beside it, or followed along a drawn leader line (leader-following arms only on multi-pen sheets, where the annotation pen separates from the work)",
                  "enum": [
                    "adjacent",
                    "leader"
                  ],
                  "type": "string"
                },
                "mirrored": {
                  "type": "boolean"
                },
                "rotation": {
                  "description": "Detected rotation in degrees (0 | 90 | 180 | 270)",
                  "type": "number"
                },
                "score": {
                  "description": "Length-weighted fraction of the seed's segments matched within tolerance, 0..1",
                  "type": "number"
                }
              },
              "required": [
                "at",
                "score",
                "rotation",
                "mirrored"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "rejected": {
            "description": "Placements a counter-example rejected on this sheet (#259) — never counted, always named",
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "description": "The placed symbol's centroid (image px) — the point a commit places its count marker at",
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "by": {
                  "description": "Which counter-example rejected it — 1-based index into the `exclude` rects you passed",
                  "maximum": 9007199254740991,
                  "minimum": -9007199254740991,
                  "type": "integer"
                },
                "evidence": {
                  "description": "Fraction of that counter-example's discriminating linework found at this placement, 0..1 (rejection bar 0.5)",
                  "type": "number"
                },
                "extra": {
                  "description": "Richer-variant disclosure: the fraction of the seed's total length found as UNMATCHED extra linework fully inside this placement's footprint, present when past the 0.30 bar — the classic grille-counted-as-register shape; LOOK at these first. Under variant_guard such placements demote to withheld instead of matching",
                  "type": "number"
                },
                "label": {
                  "description": "The drawing's own tag for this placement (#308) — a fixture token written beside it or connected by a drawn leader (e.g. \"P-7\", \"FD1\"). Disclosure, never a recount: a match with NO label in a labeled family was counted on shape alone (look before trusting), and a withheld row carrying the seed's own tag is the drawing vouching for it",
                  "type": "string"
                },
                "label_via": {
                  "description": "How the tag reached this placement: written beside it, or followed along a drawn leader line (leader-following arms only on multi-pen sheets, where the annotation pen separates from the work)",
                  "enum": [
                    "adjacent",
                    "leader"
                  ],
                  "type": "string"
                },
                "mirrored": {
                  "type": "boolean"
                },
                "mode": {
                  "description": "What that counter-example was read as. \"shape\": it carries extra linework the seed does not, and that linework is present here too. \"crossing\": it carries no extra linework of its own — what marks it is a line running THROUGH it, and that line runs unbroken through this placement",
                  "enum": [
                    "shape",
                    "crossing"
                  ],
                  "type": "string"
                },
                "reason": {
                  "type": "string"
                },
                "rotation": {
                  "description": "Detected rotation in degrees (0 | 90 | 180 | 270)",
                  "type": "number"
                },
                "score": {
                  "description": "Length-weighted fraction of the seed's segments matched within tolerance, 0..1",
                  "type": "number"
                }
              },
              "required": [
                "at",
                "score",
                "rotation",
                "mirrored",
                "by",
                "mode",
                "evidence",
                "reason"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "scale_assumed": {
            "description": "#186: present when the true ratio is UNKNOWN (a scale is missing on the seed sheet or this one) and the sweep ran at 1:1 — an unstated ratio plus a zero count is not evidence of absence",
            "type": "string"
          },
          "scaled": {
            "additionalProperties": false,
            "description": "#186: present only when the seed was resized for this sheet",
            "properties": {
              "footprint_px": {
                "description": "The symbol's size on THIS sheet after the resize",
                "type": "number"
              },
              "ratio": {
                "description": "Seed-sheet px per target-sheet px, computed from the two sheets' own committed scales (upp_seed / upp_target) — stated, never scale-searched",
                "type": "number"
              },
              "segments": {
                "description": "Fingerprint segments that survived the resize and were actually searched for",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "sub_pixel_dropped": {
                "description": "Seed segments that fell below matchable length when scaled down — excluded from the score rather than depressing it, so a score here is a fraction of what survived, not of the whole seed",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "tol_px": {
                "description": "The endpoint tolerance actually applied — it rides the ratio up when the seed is magnified (its drawn jitter magnifies too) and never down",
                "type": "number"
              }
            },
            "required": [
              "ratio",
              "segments",
              "sub_pixel_dropped",
              "footprint_px",
              "tol_px"
            ],
            "type": "object"
          },
          "sheet": {
            "type": "string"
          },
          "withheld": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "at": {
                  "additionalItems": false,
                  "description": "The placed symbol's centroid (image px) — the point a commit places its count marker at",
                  "items": [
                    {
                      "type": "number"
                    },
                    {
                      "type": "number"
                    }
                  ],
                  "maxItems": 2,
                  "minItems": 2,
                  "type": "array"
                },
                "extra": {
                  "description": "Richer-variant disclosure: the fraction of the seed's total length found as UNMATCHED extra linework fully inside this placement's footprint, present when past the 0.30 bar — the classic grille-counted-as-register shape; LOOK at these first. Under variant_guard such placements demote to withheld instead of matching",
                  "type": "number"
                },
                "label": {
                  "description": "The drawing's own tag for this placement (#308) — a fixture token written beside it or connected by a drawn leader (e.g. \"P-7\", \"FD1\"). Disclosure, never a recount: a match with NO label in a labeled family was counted on shape alone (look before trusting), and a withheld row carrying the seed's own tag is the drawing vouching for it",
                  "type": "string"
                },
                "label_via": {
                  "description": "How the tag reached this placement: written beside it, or followed along a drawn leader line (leader-following arms only on multi-pen sheets, where the annotation pen separates from the work)",
                  "enum": [
                    "adjacent",
                    "leader"
                  ],
                  "type": "string"
                },
                "mirrored": {
                  "type": "boolean"
                },
                "reason": {
                  "type": "string"
                },
                "rotation": {
                  "description": "Detected rotation in degrees (0 | 90 | 180 | 270)",
                  "type": "number"
                },
                "score": {
                  "description": "Length-weighted fraction of the seed's segments matched within tolerance, 0..1",
                  "type": "number"
                }
              },
              "required": [
                "at",
                "score",
                "rotation",
                "mirrored",
                "reason"
              ],
              "type": "object"
            },
            "type": "array"
          }
        },
        "required": [
          "sheet",
          "found",
          "matches",
          "withheld",
          "candidates",
          "complete",
          "elapsed_ms"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "skipped": {
      "description": "Set scope only: every sheet excluded from counting, with role and reason — including the seed's own sheet when it is not a plan",
      "items": {
        "additionalProperties": false,
        "properties": {
          "reason": {
            "type": "string"
          },
          "role": {
            "description": "The sheet's graph role (plan / schedule / legend / detail / …)",
            "type": "string"
          },
          "sheet": {
            "type": "string"
          }
        },
        "required": [
          "sheet",
          "role",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "warning": {
      "description": "Present when the work cap dropped candidates — what a tighter seed rect would recover",
      "type": "string"
    },
    "withheld": {
      "description": "Sheet scope only. Near-matches in the [0.75, 0.92) band — reported with a reason, NEVER committed. A withheld placement is a question you can answer with view_sheet; a hidden one is a miscount",
      "items": {
        "additionalProperties": false,
        "properties": {
          "at": {
            "additionalItems": false,
            "description": "The placed symbol's centroid (image px) — the point a commit places its count marker at",
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "extra": {
            "description": "Richer-variant disclosure: the fraction of the seed's total length found as UNMATCHED extra linework fully inside this placement's footprint, present when past the 0.30 bar — the classic grille-counted-as-register shape; LOOK at these first. Under variant_guard such placements demote to withheld instead of matching",
            "type": "number"
          },
          "label": {
            "description": "The drawing's own tag for this placement (#308) — a fixture token written beside it or connected by a drawn leader (e.g. \"P-7\", \"FD1\"). Disclosure, never a recount: a match with NO label in a labeled family was counted on shape alone (look before trusting), and a withheld row carrying the seed's own tag is the drawing vouching for it",
            "type": "string"
          },
          "label_via": {
            "description": "How the tag reached this placement: written beside it, or followed along a drawn leader line (leader-following arms only on multi-pen sheets, where the annotation pen separates from the work)",
            "enum": [
              "adjacent",
              "leader"
            ],
            "type": "string"
          },
          "mirrored": {
            "type": "boolean"
          },
          "reason": {
            "type": "string"
          },
          "rotation": {
            "description": "Detected rotation in degrees (0 | 90 | 180 | 270)",
            "type": "number"
          },
          "score": {
            "description": "Length-weighted fraction of the seed's segments matched within tolerance, 0..1",
            "type": "number"
          }
        },
        "required": [
          "at",
          "score",
          "rotation",
          "mirrored",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "scope",
    "found",
    "seed",
    "complete"
  ],
  "type": "object"
}
sha256:45efa30fe4491c94a3ae774c476cffdf15200142485f439f668679dd905c799b

Description hash: sha256:ba8ee2b05abb349c0a88affd76d26d71629ef2817591c62063c153cd7a872801

Interface hash: sha256:7144bd90e0df5d308f11c70e58940255edabb284ccf9a5fa146444650d19fef4

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/symbol_sweep",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "symbol_sweep"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:2e5a7d9d055fdfcff5fbb3d40d0cff5bc6084616afee672c3d10b5ff91fea880"
}
toolunknown0.9.990.9.100
takeoff_summarykentucky-ai-opentakeoff:tool:takeoff_summary
Observed interface and hashes

Per-condition totals (floor/wall/border SF, LF, EA, SY, with and without waste) plus grand totals — the Report's numbers, computed by the same rules. Numbers only: the deliverable that SHOWS the work on the drawings is export_marked_pdf. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {},
  "type": "object"
}
sha256:73fc3af6ba54a1293c44f954cf944c40d069a764ef7974e6fc74addd4231b225

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "conditions": {
      "items": {
        "additionalProperties": {},
        "properties": {
          "border_sf": {
            "type": "number"
          },
          "border_sf_net": {
            "type": "number"
          },
          "ea": {
            "type": "number"
          },
          "finish_tag": {
            "type": "string"
          },
          "floor_sf": {
            "type": "number"
          },
          "floor_sf_net": {
            "type": "number"
          },
          "id": {
            "type": "string"
          },
          "lf": {
            "type": "number"
          },
          "lf_net": {
            "type": "number"
          },
          "multiplier": {
            "type": "number"
          },
          "shape_count": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "sy_net": {
            "type": "number"
          },
          "total_sf": {
            "type": "number"
          },
          "total_sf_net": {
            "type": "number"
          },
          "wall_sf": {
            "type": "number"
          },
          "wall_sf_net": {
            "type": "number"
          },
          "waste_pct": {
            "type": "number"
          }
        },
        "required": [
          "id",
          "finish_tag",
          "multiplier",
          "waste_pct",
          "shape_count",
          "floor_sf",
          "wall_sf",
          "border_sf",
          "lf",
          "ea",
          "total_sf",
          "floor_sf_net",
          "wall_sf_net",
          "border_sf_net",
          "lf_net",
          "total_sf_net",
          "sy_net"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "proposals": {
      "description": "The proposal ledger (#365): per batch, how many shapes are still pending, how many the estimator accepted, whether it was withdrawn, and which batch new commits attach to (current). Present only when a proposal exists",
      "items": {
        "additionalProperties": false,
        "properties": {
          "accepted": {
            "description": "Shapes from the batch the estimator already accepted — ink, outside every agent verb",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "current": {
            "const": true,
            "description": "New agent commits attach to this batch",
            "type": "boolean"
          },
          "label": {
            "type": "string"
          },
          "pending": {
            "description": "Shapes attached to the batch and not yet affirmed by a human",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "proposal_id": {
            "type": "string"
          },
          "rationale": {
            "type": "string"
          },
          "withdrawn": {
            "const": true,
            "type": "boolean"
          }
        },
        "required": [
          "proposal_id",
          "label",
          "rationale",
          "pending",
          "accepted"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "proposed_condition_edits": {
      "description": "Pending condition-edit diffs (#365) beside the current knobs. The rows above are the CURRENT values — nothing changes until the estimator accepts. Present only when any are pending",
      "items": {
        "additionalProperties": false,
        "properties": {
          "condition": {
            "type": "string"
          },
          "condition_id": {
            "type": "string"
          },
          "current": {
            "additionalProperties": {},
            "description": "The condition's knobs as they stand — what every total above is computed from",
            "properties": {
              "drop_ft": {
                "type": "number"
              },
              "finish_tag": {
                "type": "string"
              },
              "height_ft": {
                "type": "number"
              },
              "multiplier": {
                "type": "number"
              },
              "rise_ft": {
                "type": "number"
              },
              "roll_setup": {
                "anyOf": [
                  {
                    "additionalProperties": {},
                    "properties": {},
                    "type": "object"
                  },
                  {
                    "type": "null"
                  }
                ]
              },
              "waste_pct": {
                "type": "number"
              }
            },
            "type": "object"
          },
          "proposal_id": {
            "type": "string"
          },
          "proposed": {
            "additionalProperties": {},
            "description": "Only the fields that would change",
            "properties": {
              "drop_ft": {
                "type": "number"
              },
              "finish_tag": {
                "type": "string"
              },
              "height_ft": {
                "type": "number"
              },
              "multiplier": {
                "type": "number"
              },
              "rise_ft": {
                "type": "number"
              },
              "roll_setup": {
                "anyOf": [
                  {
                    "additionalProperties": {},
                    "properties": {},
                    "type": "object"
                  },
                  {
                    "type": "null"
                  }
                ]
              },
              "waste_pct": {
                "type": "number"
              }
            },
            "type": "object"
          },
          "proposed_at": {
            "type": "string"
          },
          "rationale": {
            "type": "string"
          }
        },
        "required": [
          "proposal_id",
          "condition",
          "condition_id",
          "current",
          "proposed",
          "rationale",
          "proposed_at"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "scale_unconfirmed": {
      "description": "Sheets whose scale is agent-set and no human has confirmed — these totals stand on an unverified scale; verify against a stated dimension or confirm in the canvas",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "shared_floor_sf": {
      "description": "Scope collision (#366): floor claimed by more than one shape across the whole takeoff, counted once per cell (Σ areas − union), in SF through each sheet's scale. Has to read 0 before a total means anything — scope_duplicates names the pairs",
      "type": "number"
    },
    "shared_floor_unmeasured": {
      "description": "Floor shapes the collision check could not measure (unscaled sheet, degenerate ring) — left OUT of shared_floor_sf rather than counted as zero; present only when any",
      "items": {
        "additionalProperties": false,
        "properties": {
          "reason": {
            "type": "string"
          },
          "shape_id": {
            "type": "string"
          },
          "sheet_id": {
            "type": "string"
          }
        },
        "required": [
          "shape_id",
          "sheet_id",
          "reason"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "totals": {
      "additionalProperties": {},
      "properties": {
        "ea": {
          "type": "number"
        },
        "lf": {
          "type": "number"
        },
        "lf_net": {
          "type": "number"
        },
        "sy_net": {
          "type": "number"
        },
        "total_sf": {
          "type": "number"
        },
        "total_sf_net": {
          "type": "number"
        }
      },
      "required": [
        "total_sf",
        "total_sf_net",
        "lf",
        "lf_net",
        "ea",
        "sy_net"
      ],
      "type": "object"
    }
  },
  "required": [
    "conditions",
    "totals",
    "shared_floor_sf"
  ],
  "type": "object"
}
sha256:3d948f608dc208a1ca7fe49f6ecbfe2fca5dd6b983e29cfae4637defe9ae8c23

Description hash: sha256:778fa82f920f97bed4b2177bb29bb2d36db31c9ac8996085f6d85ac1841633b3

Interface hash: sha256:3f17d4dcd80dc05ae63271163cf9968e94696f49c3a211e716100ffe272aab5f

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/takeoff_summary",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "takeoff_summary"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:571c3c0282e8610caa41a3a5c721938ba822c2de631aab4d6d4bb1062221c856"
}
toolunknown0.9.990.9.100
undo_lastkentucky-ai-opentakeoff:tool:undo_last
Observed interface and hashes

Step back over your OWN last n mutations, newest first — a committed measure_polygon, an edit_shape, a delete_shape, an edit_materials call, an edit_condition call, or an RFI verb (create_rfi / resolve_rfi / delete_rfi). Each step is reversed exactly (a commit is removed, an edit is restored verbatim, a delete is re-inserted where it was, a materials edit's whole array is restored, a condition edit's waste/multiplier pair is restored), so this restores state rather than approximating it. Reads are never journaled, so n counts gestures that changed something, not tool calls you made. Use it when a sweep committed against the wrong condition or a batch went in on the wrong sheet — one call instead of N deletes. Scope: this session's own history only. It is not the browser canvas's undo stack, and load_plan clears it along with the shapes it refers to.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "n": {
      "default": 1,
      "description": "How many steps to reverse (1–100)",
      "maximum": 100,
      "minimum": 1,
      "type": "integer"
    }
  },
  "type": "object"
}
sha256:438a8d54df2d38607b2ddbbc9668ccd213b5ec7b3d46989e55ba9d12377c58de

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "note": {
      "type": "string"
    },
    "remaining": {
      "description": "Steps still available to undo",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "shape_count": {
      "description": "Committed shapes after the undo",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "steps": {
      "description": "Newest first",
      "items": {
        "additionalProperties": false,
        "properties": {
          "op": {
            "enum": [
              "commit",
              "scale",
              "edit",
              "annotation_text",
              "delete",
              "materials",
              "condition",
              "approval",
              "duplicate_condition",
              "split_condition",
              "cutout",
              "cutout_restore",
              "runcut",
              "rfi_create",
              "rfi_resolve",
              "rfi_delete",
              "proposal_open",
              "proposal_revise",
              "proposal_withdraw",
              "condition_proposal",
              "condition_proposal_withdraw",
              "condition_proposal_accept",
              "pricing",
              "estimate_settings"
            ],
            "type": "string"
          },
          "seq": {
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "shapes": {
            "description": "Shapes affected by reversing this step — 0 for a materials step (it restores a condition's supporting-materials rows, not shapes), for a condition step (it restores the waste/multiplier pair), and for an approval step (it re-seats or removes a verdict mark)",
            "maximum": 9007199254740991,
            "minimum": -9007199254740991,
            "type": "integer"
          },
          "tool": {
            "description": "The tool call this step came from",
            "type": "string"
          }
        },
        "required": [
          "seq",
          "op",
          "tool",
          "shapes"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "undone": {
      "description": "Steps actually reversed",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "undone",
    "steps",
    "shape_count",
    "remaining"
  ],
  "type": "object"
}
sha256:fb2f6211ca30985f235f5c2205410395b972916a75a467b8337cbd4e55501a36

Description hash: sha256:db1ae6c61090cefe88deb8c9444aa2b80224c03c46a796ead51cac1bc7a9aed5

Interface hash: sha256:bf48923baac239ff8fb83f5476c7248c4580e35ecda8431c5263081847bad3cf

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/undo_last",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "undo_last"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:c30af3ff48482354236f234d4b4435a0b897d168045488684b2aa7ef3553f2b8"
}
tooldestructive0.9.990.9.100
view_sheetkentucky-ai-opentakeoff:tool:view_sheet
Observed interface and hashes

SEE the sheet — render the page (or a crop of it) to a PNG image. This is your eyes on the plan, so CROP, DON'T SQUINT: the render downsamples to the px budget (≤2000 long side), which on an E-size sheet is ~4 sheet pixels per returned pixel — a full-sheet render finds WHERE things are, and only a tight region crop can tell you what the linework and labels actually say. Never audit a trace or read a dimension off a full-sheet render. region is in image px — the same space as every other tool — so a feature at pixel (ix, iy) of the returned image sits at x = region_x0 + ix × (region_x1 − region_x0) / img_w (same for y), and those coordinates go straight into measure_polygon, or read_sheet_text. overlay:true burns the session's committed shapes into the render (human-affirmed ink solid red, unreviewed machine shapes dashed blue) — render again after committing to verify your geometry landed where you intended, and sanity-check what you see: a fixture-sized ring where a room should be means the seed landed inside a stall or casework; an outsized ring means the flood escaped through an opening. To MEASURE rather than guess, pass grid: a calibrated measuring grid is burned in — thin lines every 1 ft, heavy blue every 5 ft, foot labels along the crop edges, feet counted from the crop's top-left corner. Count grid cells between walls exactly like an estimator scaling a plan; never derive a dimension by eye when the grid can give it to you. grid "auto" uses the sheet's set scale; before set_scale, pass the drawing scale read off the title block as inches-per-foot — "1/4" for a 1/4" = 1'-0" plan, "3/16", "0.25". marks (#297) burns DISCLOSURE layers into the render, so what a reply names, the picture shows: pass the coordinate lists a tool disclosed — question: withheld placements (orange ?-circles), struck: rejections a counter-example or luminance gate refused (magenta struck ×), ring: reference points like the sweep's own seed (violet double ring). The colors sit deliberately off the common CAD pens so they cannot vanish into color-plotted work. An overlay audit without marks shows only committed ink — the validation trap where 37 disclosed near-misses read as "it missed them". Rendering needs the optional native canvas (@napi-rs/canvas); where it isn't installed this tool errors cleanly and every other tool still works. Coordinates are image px at render scale 2.0: PDF pt × 2, origin top-left, y down (the browser canvas's native space). Sheet payloads carry dims in both px and pt.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "grid": {
      "description": "Burn in a calibrated 1-ft/5-ft measuring grid: \"auto\" = the sheet's set scale; otherwise the drawing scale as inches-per-foot, e.g. \"1/4\", \"3/16\", \"0.25\"",
      "type": "string"
    },
    "marks": {
      "description": "Disclosure marks to burn into the render (#297): what the reply names, the picture shows. Coordinates in image px",
      "properties": {
        "question": {
          "description": "Open questions — withheld placements, spots to look at. Orange ?-in-circle",
          "items": {
            "additionalItems": false,
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "type": "array"
        },
        "ring": {
          "description": "Reference points — the sweep's seed.center, an anchor. Violet double ring",
          "items": {
            "additionalItems": false,
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "type": "array"
        },
        "struck": {
          "description": "Refusals — rejected[] placements, lum_gate.at. Magenta struck ×",
          "items": {
            "additionalItems": false,
            "items": [
              {
                "type": "number"
              },
              {
                "type": "number"
              }
            ],
            "maxItems": 2,
            "minItems": 2,
            "type": "array"
          },
          "type": "array"
        }
      },
      "type": "object"
    },
    "overlay": {
      "description": "Burn committed shapes into the render (solid = human-affirmed, dashed = unreviewed)",
      "type": "boolean"
    },
    "px": {
      "description": "Long-side pixel budget of the returned image (default 1400) — small region + high px = readable dimension strings",
      "maximum": 2000,
      "minimum": 200,
      "type": "integer"
    },
    "region": {
      "description": "Crop rect in image px (origin top-left, y down); omit for the full sheet",
      "properties": {
        "x0": {
          "type": "number"
        },
        "x1": {
          "type": "number"
        },
        "y0": {
          "type": "number"
        },
        "y1": {
          "type": "number"
        }
      },
      "required": [
        "x0",
        "y0",
        "x1",
        "y1"
      ],
      "type": "object"
    },
    "sheet": {
      "type": "string"
    }
  },
  "required": [
    "sheet"
  ],
  "type": "object"
}
sha256:d1889580c210dbaff97d98c3819f472fee83c28c1a8edd0b0b558f323553cbab

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:1fb3326d1d5e3e98e3acffdcaa55d0a074098e336836afe15022a223e124056d

Interface hash: sha256:6a7a214dc7cb08285c9e62e9dc0885b2b6a066d682c873e8762037e8d8650fda

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/view_sheet",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "view_sheet"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:09f9d931501e60993236bdcdea64183285fac4def670bd4245db8777c4038b56"
}
toolunknown0.9.990.9.100
withdraw_condition_editkentucky-ai-opentakeoff:tool:withdraw_condition_edit
Observed interface and hashes

Drop a pending condition-edit proposal (#365) without touching the condition. undo_last re-seats it.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "proposal_id": {
      "description": "From propose_condition_edit, or takeoff_summary's proposed_condition_edits",
      "type": "string"
    }
  },
  "required": [
    "proposal_id"
  ],
  "type": "object"
}
sha256:2f171981eaf226e58ee2b0375c2bebf224653189f76b3f6464d0dd7212827089

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "condition": {
      "type": "string"
    },
    "proposal_id": {
      "type": "string"
    },
    "withdrawn": {
      "const": true,
      "type": "boolean"
    }
  },
  "required": [
    "proposal_id",
    "condition",
    "withdrawn"
  ],
  "type": "object"
}
sha256:ae611c403066716292a9a3b495a35a19521de827eb96bd3933c44c81de21c3ed

Description hash: sha256:81a7d32003faaea9ac32c1b44d0e5c8aef8858789e5af5bc19bb0ab3e01b40c0

Interface hash: sha256:ce99e0264272cf4cbf2a728ff1f2cd7785a21b63761118e1f47bdbff5c2c3e65

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/withdraw_condition_edit",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "withdraw_condition_edit"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:80f0dd682f4d9d269962ba7233ef80eda86c95707b700a835dcafe22bdb296c1"
}
toolunknown0.9.990.9.100
withdraw_proposalkentucky-ai-opentakeoff:tool:withdraw_proposal
Observed interface and hashes

Take a proposal back (#365): every still-pending shape in the batch is removed in ONE journal step, the record stays marked withdrawn (its label is history the estimator may still read), and new commits stop attaching to it. Shapes the estimator already accepted are ink and stay — the reply counts them. This is the honest exit for "that batch was wrong" — one call instead of N delete_shape calls, and undo_last restores the whole batch.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "proposal_id": {
      "description": "The batch, from propose_takeoff",
      "type": "string"
    }
  },
  "required": [
    "proposal_id"
  ],
  "type": "object"
}
sha256:a354d0bab06acd769eeb58ce097668b7a64132c7e306b53f42d30f5b3ee0e86b

Output schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "accepted_kept": {
      "description": "Shapes from the batch the estimator had accepted — untouched",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    },
    "label": {
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "proposal_id": {
      "type": "string"
    },
    "withdrawn": {
      "description": "Pending shapes removed",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "type": "integer"
    }
  },
  "required": [
    "proposal_id",
    "label",
    "withdrawn",
    "accepted_kept",
    "note"
  ],
  "type": "object"
}
sha256:8e705f045838e4f91d20fe17663dce9bb2879604097eb2c7763c2e8d748c9a72

Description hash: sha256:89001c1e312ee0959cea213e926633a88d7eda56dc62008fabe81d27ac330d0c

Interface hash: sha256:82fe248ed825cd37dd358e1e5f361f2e003ad5d1fd203f8c93c4ebcdcfcec96d

Other observed Modelara metadata
{
  "id": "mcp:opentakeoff/withdraw_proposal",
  "source": {
    "type": "mcp",
    "server": "opentakeoff",
    "operation": "withdraw_proposal"
  },
  "declared": {
    "read_only": "unknown",
    "destructive": "unknown",
    "idempotent": "unknown",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "unknown",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "absent"
  },
  "fingerprint": "sha256:d6233ebbb2adfb0f662a79e36cc3c0d67ead625bf8ec41e6008a145f21f80592"
}
toolunknown0.9.990.9.100

STATIC COMPARISONS

Release history

2 release transitions
  1. 4 added0 removed4 schema0 write0 destructive4 unknown

    Nov 16, 2026· Pending human review

  2. 0 added0 removed58 schema0 write0 destructive0 unknown

    Nov 16, 2026· Pending human review