Skip to main content
Glama
danielproxd2

MCP_CAD

by danielproxd2

list_faces

List faces of solid bodies, returning centroid, normal, area, and type for each face to enable selection by spatial reasoning for sketching and extruding.

Instructions

Listar caras — enumerate faces of one or all solid bodies.

Mirror of list_edges for faces. Returns one dict per face with: - index: 0-based per-body. NOT durable across rebuilds. - body_name: which body the face belongs to. - type: "planar" | "cylindrical" | "conical" | "spherical" | "other". Informational; addressing is by centroid. - centroid_mm: [x, y, z] in mm — midpoint of the face's bounding box. DURABLE reference for create_sketch_on_face. - area_mm2: face area in mm² (None if SW didn't expose it). - normal: outward normal [nx, ny, nz] for planar faces; None if SW didn't expose it. OMITTED on non-planar faces (token economy — structurally N/A there). - radius_mm, axis, concave: for cylindrical faces only — the geometry-side bore Ø used by verify_build_report; concave True = bore wall, False = outer boss/step face, None = unknown. OMITTED on non-cylindrical faces. - box_mm: axis-aligned bounding box [xmin,ymin,zmin,xmax,ymax, zmax] in mm (None if SW didn't expose it) — lets verify_build_report derive through-vs-blind from geometry (a bore face spanning both ends of the body is a through cut, regardless of the feature-definition read).

Args: body_name: If given, return only faces of that body. Else return faces of every solid body in the active part.

Use case: chained-feature LLM workflow. The LLM lists faces, reasons spatially ("the top face has the largest +Z normal"), passes the centroid to create_sketch_on_face, then sketches and extrudes/cuts on it.

Caveat: per-body face ordering is determined by SW's internal topology and is NOT durable across rebuilds. Re-run list_faces immediately before create_sketch_on_face rather than caching centroids across model edits.

Example — find the top face of a 50x50x20 block (sketched on Front, extruded +Z by 20): faces = list_faces() top = max( (f for f in faces if f["normal"] and f["normal"][2] > 0.9), key=lambda f: f["centroid_mm"][2], ) # top["centroid_mm"] = [25.0, 25.0, 20.0]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
body_nameNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

No annotations exist, so description carries full burden. It exhaustively documents return fields, durability caveats, and omitted fields for non-planar/non-cylindrical faces, ensuring full transparency.

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?

Well-structured with sections (Args, Use case, Caveat, Example). Slightly long but every sentence adds value, and the bullet format keeps it readable.

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?

Given output schema exists, description still provides rich detail on all return fields, edge cases, and an example, making it fully self-contained for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, body_name, is fully explained: if given, filter to that body; else all bodies. Schema has no description (0% coverage), but this description completely compensates.

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 description states 'enumerate faces of one or all solid bodies' and explicitly frames it as a mirror of list_edges for faces, clearly distinguishing its purpose.

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?

Provides clear when to use via the body_name parameter and describes a chained-feature use case. Missing explicit 'when not to use' or alternative tool mention, but still strong.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/danielproxd2/solidworks-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server