Skip to main content
Glama
FullyDefined – AI for SOLIDWORKS

FullyDefined – AI for SOLIDWORKS

solidworks_guide

Returns read-only guidance for operating SOLIDWORKS tools, including step recipes, measurement checks, units, pitfalls, and failed-call fixes. Use before multi-step builds or when unsure.

Instructions

Read how to operate SolidWorks through these tools: recipes (the order of steps and the tools for a plate with holes, a revolved part, sheet metal and its flat DXF, an assembly with mates, a finished drawing, looking inside an assembly, equations, a weldment frame), verifying by measurement, units and coordinates, pitfalls and limits, and what to do when a call fails. Call it before a multi-step build, or when unsure how to do something. Without topic it lists the topics. Every answer starts with the short rules (In short). Read-only.

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": "solidworks_guide"
  }
}

Input Schema

NameRequiredDescriptionDefault
topicNoA topic from the list: a section name (e.g. 'pitfalls'), a recipe letter (e.g. 'D') or a recipe's title words (e.g. 'sheet metal')

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are supplied, so the description must carry the behavior itself, and it does declare 'Read-only' and disclose the response shape ('Every answer starts with the short rules (In short)'). It also signals the tool doubles as a topic index when called bare. It does not state answer length, verbosity, or whether guidance is static versus document-state-aware, which keeps it out of the top band.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded and the closing guidance sentences are tight, but the middle is a single sprawling parenthetical enumerating eight recipe subjects with mixed grammatical form ('sheet metal and its flat DXF', 'looking inside an assembly'), which is hard to scan. The 'In short' formatting note sits awkwardly at the end rather than with the usage guidance.

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 one-parameter, read-only documentation lookup with no output schema and no annotations, the description covers what it returns, how to enumerate topics, and when to invoke it. Remaining gaps (answer depth, whether advice reflects current model state) are minor for this tool class.

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 baseline is 3, but the description adds real meaning beyond the schema: it explains that omitting topic returns the topic list, and it frames the fuzzy matching ('a recipe's title words') as a lookup strategy. The example topic categories (plate with holes, sheet metal, weldment frame) also help an agent guess valid inputs.

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 — 'Read how to operate SolidWorks through these tools' — and enumerates the content it covers (recipes, verification, units/coordinates, pitfalls, error recovery). This is unmistakably a documentation/help lookup, which cleanly separates it from every sibling tool (add_mate, create_sketch, etc.) that performs CAD actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit trigger conditions: 'Call it before a multi-step build, or when unsure how to do something,' plus the discovery path 'Without topic it lists the topics.' That covers both direct need and exploration. No explicit when-not guidance, but for a read-only help tool no real alternative exists among the action-oriented siblings.

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

Deploy Server

Other Tools