Skip to main content
Glama
Vectorworks MCP

Vectorworks MCP

vw_export_geometry

Read-only

Exports 2D geometry from a design layer as numeric data to verify drawing contents or compare fill and pen attributes before matching styles.

Instructions

Read the 2D geometry of one design layer as numbers, in document units.

Read-only. Lines and polygons come as points, arcs as centre / radius / angles, texts with origin and string, dimensions with their text; groups are descended, plug-in objects (chain dimensions, doors) are one entry each. Use it to verify what is really in the file, or to compare fill and pen attributes with neighbouring objects before drawing in the same style; vw_render_layers draws the same data as a picture, vw_screenshot shows the real window instead. Returns {document, layer, objects: [{type, class, uuid, points | origin | center, attrs?...}], truncated}, or with out_path {path, count, by_type, by_class, extent}.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "vw_export_geometry"
  }
}

Input Schema

NameRequiredDescriptionDefault
layerNoName of the design layer to read. Default: the active layer.
limitNoMaximum number of objects to export; the result says `truncated` when the layer has more. Default 20000.
classesNoOnly objects in these classes (exact names). Default: every class.
timeoutNoSeconds to wait for Vectorworks once it has taken the job. Default 60.
out_pathNoFile path on this Mac ("~" is expanded). When given, the full JSON is written there and only a summary comes back; use it for large layers to keep the conversation small. Default: the geometry is returned inline.
attributesNoTrue (default): each object also carries `attrs` with its fill (pattern 0 none / 1 solid background colour / 2 solid foreground colour, colours as #rrggbb), its pen (colour, weight in mils, style) and whether each follows the class (`by_class`). False: geometry only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.1.1
    • addedInput schema / properties / attributes / description
      Added value: +"True (default): each object also carries `attrs` with its fill (pattern 0 none / 1 solid background colour / 2 solid foreground colour, colours as #rrggbb), its pen (colour, weight in mils, style) and whether each follows the class (`by_class`). False: geometry only."
    • addedInput schema / properties / classes / description
      Added value: +"Only objects in these classes (exact names). Default: every class."
    • addedInput schema / properties / layer / description
      Added value: +"Name of the design layer to read. Default: the active layer."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of objects to export; the result says `truncated` when the layer has more. Default 20000."
    • addedInput schema / properties / out_path / description
      Added value: +"File path on this Mac (\"~\" is expanded). When given, the full JSON is written there and only a summary comes back; use it for large layers to keep the conversation small. Default: the geometry is returned inline."
    • addedInput schema / properties / timeout / description
      Added value: +"Seconds to wait for Vectorworks once it has taken the job. Default 60."
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnly and openWorld=false; the description adds substantial context on top: how arcs, texts, dimensions, groups and plug-in objects are represented, that limit triggers a `truncated` flag, and that out_path swaps the inline payload for a file plus summary. It also discloses the exact return object shapes, which the annotations do not cover.

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?

Front-loaded with purpose, then usage, then return shape — a sensible order with no filler sentences. The second sentence is heavily semicolon-chained and dense, which slightly slows parsing, but every clause carries information.

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

Completeness5/5

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

For a six-parameter read tool with no output schema, the description covers what is returned (both inline and file modes), element-type handling, and truncation. An agent has everything needed to call it and interpret the result.

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

Parameters3/5

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

Schema description coverage is 100%, so the six parameters are already fully documented including defaults. The description restates the out_path summary behavior and the limit/truncated relationship but adds no syntax or format detail beyond what the schema states, making 3 the appropriate baseline.

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 and resource ('Read the 2D geometry of one design layer') and adds scope ('as numbers, in document units'). It explicitly separates itself from vw_render_layers (picture) and vw_screenshot (real window), so an agent can pick correctly without opening a schema.

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 concrete use cases — verifying what is really in the file, comparing fill/pen attributes before drawing in the same style — and names the two alternatives plus the condition that selects them. Nothing 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.