Skip to main content
Glama
Vectorworks MCP

Vectorworks MCP

vw_doctor

Diagnoses why Vectorworks MCP is not responding by checking bridge installation, job files, and config without touching Vectorworks; optionally repairs stale files and reinstalls the bridge.

Instructions

Check this Vectorworks MCP setup on this Mac without touching Vectorworks.

Checks: bridge installed in the right Plug-ins folder and up to date (with its check tables), the 'MCP Run Job' command file present, Claude Desktop / Claude Code configured for this Vectorworks version, Vectorworks running, stale job files, recent log errors. Returns {ok, checks: [{name, ok (true / false / null = could not check here), detail, fix}], next_step, installed?}. Use it first when vw_ping fails; vw_ping is the live test that this one deliberately does not do. Not checked here: whether 'MCP Run Job' is in a menu and the macOS Automation permission.

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_doctor"
  }
}

Input Schema

NameRequiredDescriptionDefault
fixNoFalse (default): only report. True: also remove stale job and result files and, when the bridge is missing or outdated, install it into the user's Vectorworks Plug-ins folder (the only file written outside this server's own folder); Vectorworks must then be restarted once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.1
    • addedInput schema / properties / fix / description
      Added value: +"False (default): only report. True: also remove stale job and result files and, when the bridge is missing or outdated, install it into the user's Vectorworks Plug-ins folder (the only file written outside this server's own folder); Vectorworks must then be restarted once."
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations say readOnlyHint=false and destructiveHint=false, which is consistent with the fix flag writing a bridge file; the description adds the detail annotations cannot: fix=true writes into the user's Vectorworks Plug-ins folder ('the only file written outside this server's own folder') and requires a Vectorworks restart. It also discloses the null='could not check here' tri-state in results, which is exactly the kind of behavioral nuance an agent needs.

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 purpose, then a compact checklist, then return shape, then usage order and exclusions — nothing is buried. Minor density issues remain, e.g. the ambiguous aside 'with its check tables' and a bracketed parenthetical inside the return-shape sentence that momentarily interrupts the reading flow.

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?

With no output schema, the description correctly compensates by spelling out the return object ({ok, checks: [{name, ok, detail, fix}], next_step, installed?}), including the meaning of a null ok value. It also states what cannot be checked, leaving only minor gaps such as expected runtime or whether checks are cheap to repeat.

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 coverage is 100% and the fix parameter already documents default false, the report-only mode, the cleanup + install behavior, and the restart requirement. The description adds no syntax or format beyond that, so this is the standard baseline-3 case where the schema does the work.

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: 'Check this Vectorworks MCP setup on this Mac without touching Vectorworks.' It then enumerates exactly what is inspected (bridge install/version, 'MCP Run Job' command file, Claude Desktop/Code config, Vectorworks running, stale jobs, log errors), which is far beyond restating the name, and it explicitly separates itself from the sibling vw_ping.

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 an explicit routing rule: 'Use it first when vw_ping fails; vw_ping is the live test that this one deliberately does not do.' It also names exclusions — menu presence and macOS Automation permission are not checked — so the agent knows when this tool will be inconclusive rather than guessing.

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