Skip to main content
Glama
fusion-cam

fusion-cam

inspect

Read the active Fusion design for CAM planning: body bounding boxes/volumes, top planar face Z, horizontal faces by Z, and cylindrical holes grouped by diameter, depth, and axis. Read-only, mm.

Instructions

Describe the active design for CAM planning. Read-only. All values in mm (areas mm^2, volumes mm^3), world coordinates.

Returns bodies (including occurrence proxies) with bounding boxes and volumes, the overall bbox/volume, top_face_z_mm (highest upward-facing planar face), horizontal planar faces grouped by Z with area and facing, and cylindrical holes (concave cylinders, split faces merged) grouped by diameter/depth/axis with a count, centres, entry points and through/blind. Hole depth is the cylindrical wall only (no drill point). If a call times out it may still be running in Fusion: call status, then inspect again, before retrying anything.

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": "inspect"
  }
}

Input Schema

NameRequiredDescriptionDefault
timeout_sNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it declares read-only behavior, unit conventions (mm, mm^2, mm^3), the coordinate frame, and the exact semantics of tricky return values such as top_face_z_mm and hole depth excluding the drill point. It does not cover cost/performance on large models or any permission requirements, which keeps it short of a 5.

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?

Purpose and unit conventions are front-loaded in short declaratives, followed by a dense but earned enumeration of returned entities. The timeout-recovery sentence is placed at the end rather than with the purpose, which is a minor structural weakness but no sentence is filler.

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 high-complexity geometry tool, the description covers scope, units, frame, return semantics, and timeout recovery, and an output schema exists to carry exact return structure. The missing piece is explicit routing relative to the closely named sibling 'status' and how large models affect runtime.

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?

One parameter, timeout_s, has 0% schema coverage, and the description never explains its unit, default, or effect on the call. The timeout recovery sentence gestures at timeouts generally but does not connect to the parameter, so an agent must infer the default behavior.

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 opens with a specific verb and resource: 'Describe the active design for CAM planning,' immediately scoping it to geometry inspection for CAM. It does not explicitly contrast with the sibling 'status' tool, so an agent must infer the split between inspecting geometry and checking job/server status.

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

Usage Guidelines3/5

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

There is real usage guidance, but it is failure-path guidance only: on timeout, 'call status, then inspect again, before retrying anything.' That names a sibling and a sequencing rule. There is no statement of when to call inspect versus status, screenshot, or import_step during normal workflow.

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