Skip to main content
Glama
solidworks-mcp

solidworks-mcp

list_faces

Read-onlyIdempotent

Lists faces of the active part or a specified feature, with type, on-face point, area, normal, and cylinder data for selecting, measuring, or referencing faces instead of guessing coordinates.

Instructions

Faces of the active part (or only those created by 'feature'), each with its type, a point lying ON it (point_mm, model coordinates: pass it to select_face_at_point, hole, shell, fillet face_points, create_plane face_point...), area, outward normal of planar faces, and diameter / axis of cylinders (concave=True for holes). Use it instead of guessing coordinates.

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": "list_faces"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of faces returned
featureNo
face_typeNoany

Output Schema

NameRequiredDescriptionDefault
countYes
facesYes
totalYes
truncatedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A3.6/5.0
Behavior3/5

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

Read-only, idempotent, non-destructive behavior is already declared by the annotations, so the description's job is to add beyond that. It contributes that point_mm is in model coordinates and lies ON the face, that concave=True marks holes, and that the outward normal is only supplied for planar faces — genuine behavioral detail rather than repetition. It's silent on truncation when limit is hit and on what happens when the feature filter matches nothing.

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?

One dense sentence, front-loaded with the resource and its scope before the field inventory, and the parenthetical pointing at downstream consumers is informative rather than filler. The nested parentheses make it harder to scan than it needs to be, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the field-by-field return description is partly redundant with structured data, and annotations cover the safety profile. What remains unaddressed is behavioral consequence: whether limit silently truncates the list and how to page past it, which matters for an agent enumerating faces on a complex part.

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 only 33%: limit carries its own description, but feature and face_type do not, so the description must compensate. It does explain feature ("or only those created by 'feature'"), yet face_type's semantics go undiscussed beyond a self-explanatory enum, which leaves a partial gap for a low-coverage schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource concretely (faces of the active part) and enumerates the payload fields returned: type, the point lying on it in model coordinates, area, outward normal of planar faces, and diameter/axis for cylinders. That is enough for an agent to distinguish it from siblings like list_edges, though it never names an alternative and the verb is only implied by the name.

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?

It gives an explicit directive: "Use it instead of guessing coordinates," and spells out the follow-on calls the returned point_mm feeds into (select_face_at_point, hole, shell, fillet face_points, create_plane face_point). It does not describe when-not to use it or how it relates to list_edges for mixed geometry selection.

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