Skip to main content
Glama
Vectorworks MCP

Vectorworks MCP

vw_render_layers

Read-only

Draw design layers as PNG images from their real geometry for visual checking, even when hidden and without Screen Recording. Renders fills and line weights; texts, hatches and symbols appear simplified.

Instructions

Draw design layers as a PNG from their real geometry, whatever the Vectorworks window shows.

Read-only; one geometry job per layer, no Screen Recording needed. Use it to check drawing work on any layer, visible or hidden; vw_screenshot shows the real window instead (and any blocking dialog), vw_export_geometry returns the same data as numbers. It is a check picture, not a plot: object colours, solid fills and line weights are shown; hatches, dash styles, opacity and curved polyline segments are not, texts are marked with a small cross at their origin, and symbols / plug-in objects are grey boxes. Returns the image.

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_render_layers"
  }
}

Input Schema

NameRequiredDescriptionDefault
bboxNo[x_min, y_min, x_max, y_max] in document units to zoom in on. Default: everything on the chosen layers.
fillsNoTrue (default): paint solid fills (always below all lines). False: outlines only.
layersNoDesign layer names, drawn in this order (later ones on top). Default: the active layer only.
classesNoOnly objects in these classes (exact names). Default: every class.
timeoutNoSeconds to wait for Vectorworks per layer once it has taken the job. Default 60.
max_sizeNoLength of the image's long side in pixels. Default 1600.
out_pathNoFile path on this Mac to also save the PNG to ("~" is expanded). Default: the image is only returned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.1.1
    • addedInput schema / properties / bbox / description
      Added value: +"[x_min, y_min, x_max, y_max] in document units to zoom in on. Default: everything on the chosen layers."
    • addedInput schema / properties / classes / description
      Added value: +"Only objects in these classes (exact names). Default: every class."
    • addedInput schema / properties / fills / description
      Added value: +"True (default): paint solid fills (always below all lines). False: outlines only."
    • addedInput schema / properties / layers / description
      Added value: +"Design layer names, drawn in this order (later ones on top). Default: the active layer only."
    • addedInput schema / properties / max_size / description
      Added value: +"Length of the image's long side in pixels. Default 1600."
    • addedInput schema / properties / out_path / description
      Added value: +"File path on this Mac to also save the PNG to (\"~\" is expanded). Default: the image is only returned."
    • addedInput schema / properties / timeout / description
      Added value: +"Seconds to wait for Vectorworks per layer 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 read-only and closed-world, but the description adds real operating context: one geometry job per layer, no Screen Recording permission required, and an explicit fidelity list of what is rendered (colours, solid fills, line weights) versus what is lost (hatches, dash styles, opacity, curved segments, text as crosses, symbols as grey boxes). That is exactly the kind of behavioural disclosure annotations cannot carry.

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 and read-only status, then alternatives, then caveats, then return value — a logical order. The fidelity sentence is long and clause-dense but each clause carries distinct information an agent would otherwise have to discover by trial.

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?

No output schema exists, and the description closes that gap by stating "Returns the image" and enumerating rendering limitations so the agent knows what the picture can and cannot prove. For a seven-parameter render tool with safety annotations already present, nothing essential is missing.

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 every one of the seven parameters is already documented, including defaults and units. The description adds only marginal framing (per-layer job semantics that inform the timeout) and does not explain interactions such as how bbox relates to layers. Baseline 3 applies when the schema does the heavy lifting.

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?

"Draw design layers as a PNG from their real geometry" gives a specific verb and resource, and the clause "whatever the Vectorworks window shows" immediately establishes how it differs from window-based capture. An agent can distinguish it from vw_screenshot and vw_export_geometry without opening any 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?

Explicit when-to-use ("check drawing work on any layer, visible or hidden") plus explicit alternatives with their selection conditions: vw_screenshot for the real window and blocking dialogs, vw_export_geometry for the same data as numbers. It also sets a scope boundary: "It is a check picture, not a plot."

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