Skip to main content
Glama
Kentucky-ai

opentakeoff-mcp

by Kentucky-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

view_sheet

Render a plan sheet or crop to PNG for visual inspection. Zoom into tight regions to read linework, labels, and dimensions, or overlay geometry to verify results.

Instructions

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

TableJSON Schema
NameRequiredDescriptionDefault
pxNoLong-side pixel budget of the returned image (default 1400) — small region + high px = readable dimension strings
gridNoBurn 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"
marksNoDisclosure marks to burn into the render (#297): what the reply names, the picture shows. Coordinates in image px
sheetYes
regionNoCrop rect in image px (origin top-left, y down); omit for the full sheet
overlayNoBurn committed shapes into the render (solid = human-affirmed, dashed = unreviewed)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.19
    • addedInput schema / properties / marks
      Added value: +{
+  "additionalProperties": false,
+  "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": {
+        "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": {
+        "$ref": "#/properties/marks/properties/question/items"
+      },
+      "type": "array"
+    },
+    "struck": {
+      "description": "Refusals — rejected[] placements, lum_gate.at. Magenta struck ×",
+      "items": {
+        "$ref": "#/properties/marks/properties/question/items"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}
  2. Addedv0.1.5

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: it discloses the ≤2000px downsample budget and the ~4 sheet-pixels-per-returned-pixel tradeoff on E-size sheets, the coordinate space (render scale 2.0, PDF pt × 2, top-left origin, y down), the color semantics of committed vs unreviewed overlay ink, and the graceful failure path when @napi-rs/canvas is absent.

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

Conciseness3/5

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

Front-loading is good — 'SEE the sheet' leads. But the body is a single dense run-on with colon-chained clauses, caps emphasis, and parentheticals that make it hard to scan; most sentences carry real information, yet the density crosses from thorough into unwieldy.

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?

For a complex 6-parameter render tool with no output schema and nested marks/region objects, it covers nearly everything an agent needs: coordinate spaces, pixel budget effects, grid/marks/overlay semantics, return-scale details, and the native-canvas dependency. The only gap is that the required 'sheet' identifier is left unexplained.

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 coverage is already 83%, so the baseline is 3, and the description exceeds it: it gives the region→sheet coordinate mapping formula (region_x0 + ix × (region_x1 − region_x0) / img_w), the accepted grid values ('auto' or inches-per-foot like '1/4'/'3/16'/'0.25'), and the off-CAD-pen rationale for each marks color. The required 'sheet' parameter, however, is never explained in the description.

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

Purpose5/5

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

Opens with a specific verb+resource: 'SEE the sheet — render the page (or a crop of it) to a PNG image.' It clearly distinguishes itself from siblings that extract data (read_sheet_text, get_sheet_vectors) by being the visual render path, and the crop-vs-full-sheet framing makes the tool's role unambiguous.

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

Usage Guidelines5/5

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

Gives explicit when-to-use rules: full-sheet render 'finds WHERE things are', tight crops tell 'what the linework and labels actually say', and 'Never audit a trace or read a dimension off a full-sheet render.' It routes the agent onward — 'those coordinates go straight into measure_polygon, or read_sheet_text' — and specifies grid for measuring, overlay for post-commit verification, and marks to avoid the 'validation trap'.

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

Deploy Server

Other Tools