Skip to main content
Glama
Vectorworks MCP

Vectorworks MCP

vw_lint

Read-only

Checks Vectorworks Python scripts without running them, flagging syntax errors, wrong vs.* arguments, deprecated calls, and crash-prone functions before execution.

Instructions

Check Python meant for Vectorworks without running it.

Finds syntax errors, vs.* calls with a wrong number of arguments, deprecated calls (these would open the blocking "Script Errors" window) and functions a published safety sweep found to crash or hang Vectorworks or to open a dialog; unknown vs.* names are warnings. Works without Vectorworks running. Argument types and values are not checked here (the bridge checks types when the code runs). vw_exec_python and vw_exec_python run this check themselves, so call it directly only to check a script you do not intend to run yet. Returns {ok, errors, warnings, api}.

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_lint"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNoPython source to check. Pass either code or path, not both.
pathNoPath of a Python script file on this Mac to check instead of code, for example a menu command script. Pass either code or path, not both.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • addedInput schema / properties / code / description
      Added value: +"Python source to check. Pass either code or path, not both."
    • addedInput schema / properties / path / description
      Added value: +"Path of a Python script file on this Mac to check instead of code, for example a menu command script. Pass either code or path, not both."
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, which the description is consistent with ('works without Vectorworks running', 'without running it'). Beyond the annotations it discloses meaningful behavior: deprecated calls open a blocking 'Script Errors' window, the crash/hang list comes from a published safety sweep, unknown vs.* names are only warnings, and the return shape {ok, errors, warnings, api} is given despite no output schema.

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 layered detail (what it catches, what it does not, when to call it, return shape). Dense but every sentence carries information; the only blemish is the duplicated 'vw_exec_python and vw_exec_python' phrase, which reads as a typo.

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 two-optional-parameter read-only checker with no output schema, the description covers purpose, scope limits, interaction with siblings, and return shape. Only the duplicated sibling name and the absence of any note on how the two not-required inputs interact (both omitted) leave small gaps.

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 both parameters already document the mutual exclusion ('Pass either code or path, not both') and the file-path use case. The description adds no further per-parameter meaning, so the baseline 3 applies.

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?

The opening sentence states a specific verb and resource ('Check Python meant for Vectorworks without running it') and immediately enumerates the exact classes of problems detected (syntax errors, wrong-arity vs.* calls, deprecated calls, crash/hang functions, unknown names as warnings). This distinguishes it cleanly from vw_exec_python, which actually executes code.

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?

The description gives an explicit when-not-to-use rule: vw_exec_python runs this check itself, so call vw_lint directly 'only to check a script you do not intend to run yet.' It also states the boundary of what is checked (no argument type/value checking, that is done at run time by the bridge).

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