Skip to main content
Glama
SolidWorks MCP Python

SolidWorks MCP Python

by locense

Verify Model Against Expectations

verify_model
Read-onlyIdempotent

Check the active part or assembly against expected mass, volume, size, feature, body, mate, and interference values; returns pass/fail checks to confirm the built geometry matches intent.

Instructions

Check the active part or assembly against what you meant to build, one pass/fail check per expected value.

Use it as the last step of a build: a modelling tool's success doesn't prove the geometry is right. Give only the values you know. Units: mm, mm³, kg; bounding_box_mm is [x, y, z] in model axes. Widen relative_tolerance when your sums ignore fillets. Needs: an open part or assembly. Read-only. Returns: verdict (pass, fail, inconclusive or report_only), checks (each expected, actual, tolerance, passed; null when unmeasured) and measured. A mismatch is still status: success.

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": "verify_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
input_dataNoThe expectations, all optional: `mass_kg`, `volume_mm3`, `bounding_box_mm`, `feature_count`, `solid_body_count`, and for an assembly `component_count`, `mate_count` and `no_interference`; `relative_tolerance` (0.01) and `length_tolerance_mm` (0.1) have defaults. With none it only reports what it measured.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the prerequisite of an open part or assembly, the return shape (verdict, checks, measured), the four verdict values, null for unmeasured values, and critically that a mismatch still returns status: success. That last point prevents a caller from misreading a failed check as a tool error.

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

Conciseness5/5

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

Purpose and sequencing lead, then units, prerequisites, and return contract, with zero filler. Dense but every sentence carries information an agent needs; the terse formatting is functional rather than cryptic.

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?

For a read-only verification tool with full schema coverage and an output schema, the definition still covers prerequisites, units, tolerance tuning, verdict semantics, and the success-on-mismatch behavior. Nothing an agent needs in order to call and interpret 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, but the description adds meaning: units (mm, mm³, kg), that bounding_box_mm is [x, y, z] in model axes, and that the tolerances should be widened when expected sums exclude features like fillets. It also frames all expectations as optional via 'Give only the values you know.'

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 concrete verb and resource — 'Check the active part or assembly against what you meant to build, one pass/fail check per expected value' — including the output granularity (one check per expected value). It also implicitly separates itself from modeling/get-info siblings by warning that 'a modelling tool's success doesn't prove the geometry is right.' An agent can tell what this does without opening the schema.

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?

'Use it as the last step of a build' gives explicit sequencing guidance, and 'Give only the values you know' plus 'Widen relative_tolerance when your sums ignore fillets' tell the caller how to use it well. It does not name an alternative tool or state when-not to use it, so it stops short of the 5 bar.

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