Skip to main content
Glama
Vectorworks MCP

Vectorworks MCP

vw_screenshot

Read-only

Capture the Vectorworks document window as an image without scripting, even when a dialog blocks other tools. Check drawn results, see what is in front, and optionally map pixels to drawing coordinates.

Instructions

Capture the Vectorworks document window as an image, without going through Vectorworks.

Read-only; no job and no Apple Event (unless mapping is requested), so it works even while a dialog blocks every other tool. Use it to check drawn results or to see what is in front; vw_render_layers draws layers from their geometry instead, independent of the window. Returns the image plus JSON {window (screen geometry), path (saved PNG), in_front (dialogs or open menus that stall jobs), mapping? or mapping_error?, view?}.

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_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoPart of a document window's title, to pick one when several are open. Default: the largest document window.
mappingNoTrue: run one small job to read the view (centre, zoom, layer scale) and return `mapping`, so a pixel in the picture can be turned into drawing coordinates with vw_point_to_world (exact in Top/Plan views only). Default False: no job at all.
max_widthNoThe image is shrunk to at most this many pixels wide. Default 1600.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.1
    • addedInput schema / properties / mapping / description
      Added value: +"True: run one small job to read the view (centre, zoom, layer scale) and return `mapping`, so a pixel in the picture can be turned into drawing coordinates with vw_point_to_world (exact in Top/Plan views only). Default False: no job at all."
    • addedInput schema / properties / max_width / description
      Added value: +"The image is shrunk to at most this many pixels wide. Default 1600."
    • addedInput schema / properties / title / description
      Added value: +"Part of a document window's title, to pick one when several are open. Default: the largest document window."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint, it discloses that there is no job and no Apple Event unless mapping is requested, explains the practical consequence (usable when a dialog stalls other tools), and enumerates the returned JSON fields including in_front, which reports dialogs or open menus. This is substantive behavioral context the annotations cannot express.

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 the core action and safety profile, then the alternative, then the return shape — a sensible order. The parenthetical asides ('unless mapping is requested', the field list) are dense but each carries information; slightly compact prose costs a point.

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?

There is no output schema, but the description compensates by naming the returned image and the JSON keys (window, path, in_front, mapping/mapping_error, view). For a zero-required-parameter, read-only capture tool, nothing an agent needs to call it correctly is missing.

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 100%, so the baseline is 3; the description earns a notch above by tying the mapping flag to the 'no job' guarantee and noting the mapping/mapping_error return fields, clarifying the cost of opting in. The title and max_width semantics are left to the schema, which already documents them well.

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?

States a specific verb and resource ('Capture the Vectorworks document window as an image') plus the key mechanism ('without going through Vectorworks'), and explicitly contrasts with vw_render_layers, which draws from geometry instead. An agent can distinguish the two without opening either 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 explicit when-to-use ('check drawn results or to see what is in front') and names the alternative with the condition that selects it ('vw_render_layers draws layers from their geometry instead, independent of the window'). It also states a unique operating condition — it works while a dialog blocks every other tool — which is exactly the routing signal an agent needs.

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