opentakeoff-mcp

Overview Schema Source Related Servers Discussions Admin

export_takeoff

Export the complete takeoff annotations payload as JSON for import into OpenTakeoff, returned inline or written to a file path.

Instructions

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

TableJSON Schema

Name	Required	Description	Default
`path`	No	File path to write the payload to
`overwrite`	No	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.

Output Schema

TableJSON Schema

Name	Required	Description
`rfis`	No	Live RFI records; withdrawn tombstones are omitted
`units`	No	Present only for a metric project; absent means imperial — the app's own diff-only convention
`schema`	Yes
`shapes`	Yes
`sheets`	Yes
`markups`	Yes
`approvals`	No	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
`proposals`	No	Proposal batches (#365) — present only when any exist. Shapes reference them by origin.proposal_id; the canvas shows one Accept per batch
`conditions`	Yes
`last_group`	Yes
`sheet_tabs`	Yes
`sheet_group`	Yes
`project_name`	Yes
`sheet_levels`	No	Present only when a sheet carries a level label (the app omits it when empty)
`condition_edit_proposals`	No	Pending condition-edit diffs (#365) — present only when any exist. Nothing on the condition changes until the estimator accepts in the canvas

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.1.23Sep 12, 2026

addedOutput schema / properties / sheet_levels / description

Added value: +"Present only when a sheet carries a level label (the app omits it when empty)"

addedOutput schema / properties / units / description

Added value: +"Present only for a metric project; absent means imperial — the app's own diff-only convention"

changedOutput schema / required

Previous value: -[
-  "schema",
-  "project_name",
-  "units",
-  "sheets",
-  "conditions",
-  "shapes",
-  "markups",
-  "sheet_group",
-  "last_group",
-  "sheet_tabs",
-  "sheet_levels"
-]New value: +[
+  "schema",
+  "project_name",
+  "sheets",
+  "conditions",
+  "shapes",
+  "markups",
+  "sheet_group",
+  "last_group",
+  "sheet_tabs"
+]

Changed5 schema fields changedv0.1.21Sep 12, 2026

addedOutput schema / properties / condition_edit_proposals

Added value: +{
+  "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": true,
+    "properties": {
+      "condition_id": {
+        "type": "string"
+      },
+      "id": {
+        "type": "string"
+      },
+      "proposed": {
+        "additionalProperties": true,
+        "properties": {},
+        "type": "object"
+      },
+      "proposed_at": {
+        "type": "string"
+      },
+      "rationale": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "condition_id",
+      "proposed",
+      "rationale",
+      "proposed_at"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / proposals

Added value: +{
+  "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": true,
+    "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"
+}

addedOutput schema / properties / rfis

Added value: +{
+  "description": "Live RFI records; withdrawn tombstones are omitted",
+  "items": {},
+  "type": "array"
+}

addedOutput schema / properties / sheets / items / properties / scale_confirmed

Added value: +{
+  "description": "False for agent-set calibration until a human confirms it",
+  "type": "boolean"
+}

addedOutput schema / properties / sheets / items / properties / scale_source

Added value: +{
+  "description": "How the exported calibration was established",
+  "type": "string"
+}

Changed1 schema field changedv0.1.15Aug 6, 2026

addedInput schema / properties / overwrite

Added value: +{
+  "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"
+}

Changed1 schema field changedv0.1.12Aug 3, 2026

addedOutput schema / properties / approvals

Added value: +{
+  "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"
+}

Changed1 schema field changedv0.1.10Aug 1, 2026

changedOutput schema / properties / shapes / items / properties / origin / description

Previous value: -"Provenance: method (manual|one_click_v1), actor (omitted=human, 'agent'=MCP/automation), reviewed (human affirmed at an explicit gate), and correction fields (edited, edited_before_create, copied, proposed_verts_norm, edits)"New value: +"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)"

Changed4 schema fields changedv0.1.9Jul 31, 2026
- addedOutput schema / properties / shapes / items / properties / computed / description
```
Added value: +"count shapes carry {count} alone; every other role carries area_sf + perimeter_lf"
```
- addedOutput schema / properties / shapes / items / properties / computed / properties / count
```
Added value: +{
+  "type": "number"
+}
```
- removedOutput schema / properties / shapes / items / properties / computed / required
```
Removed value: -[
-  "area_sf",
-  "perimeter_lf"
-]
```
- changedOutput schema / properties / shapes / items / properties / measure_role / enum
```
Previous value: -[
-  "floor_area",
-  "deduct",
-  "linear"
-]New value: +[
+  "floor_area",
+  "deduct",
+  "linear",
+  "surface_area",
+  "count"
+]
```

Changed1 schema field changedv0.1.3Jul 21, 2026

changedOutput schema / properties / shapes / items / properties / origin / description

Previous value: -"Provenance for one-click traces"New value: +"Provenance: method (manual|one_click_v1), actor (omitted=human, 'agent'=MCP/automation), reviewed (human affirmed at an explicit gate), and correction fields (edited, edited_before_create, copied, proposed_verts_norm, edits)"

Addedv0.1.2Jul 17, 2026
Removedv0.1.1Jul 17, 2026
First observedJul 15, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it does well: it discloses that the payload is returned inline by default, that passing path additionally writes JSON to disk, and it documents the exact coordinate conventions (image px at scale 2.0, PDF pt × 2, top-left origin, y down) and that sheet payloads carry px and pt dims. It does not explicitly frame the operation as read-only versus file-writing in safety terms, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The definition is front-loaded with what the payload is, then adds invocation and coordinate details in compact clauses. Every sentence earns its place, though the dense coordinate-system sentence is somewhat tangential to tool selection.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, yet the description still explains the payload's identity and coordinate space. With 100% param coverage and no annotations, only the absence of explicit safety framing for the on-disk write leaves a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3, but the description adds real meaning: 'Returned inline; pass path to also write it to disk as JSON' clarifies that path is an additive side-effect flag rather than a mode selector, which the schema alone does not convey. The overwrite semantics are fully covered by the schema itself and not restated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a precise verb+resource — the full 'opentakeoff.takeoff_canvas.v1' annotations payload, exactly what the app autosaves and can re-import. This distinguishes it from the other export tools (export_dxf, export_report, export_marked_pdf) by making clear it is the native, round-trippable format. It stops short of explicitly naming those siblings, so 4 rather than 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage ('Returned inline; pass path to also write it to disk as JSON') but gives no explicit when-to-use or when-not-to-use guidance relative to the other export siblings. The condition for writing to disk is clear, but routing between export tools is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.