Skip to main content
Glama
fusion-cam

fusion-cam

cam_generate

Generates CAM toolpaths in Fusion in the background and polls until done, returning validity and checkToolpath results per operation. Resume a timed-out job by id instead of restarting.

Instructions

Generate toolpaths and wait for them (seconds). Returns each operation's toolpath validity and checkToolpath result, plus all_valid.

targets: setup or operation names (default: all operations of the last setup). Fusion generates in the background and this tool polls with short calls, so Fusion stays responsive. If timeout_s passes, generation continues in Fusion: call cam_generate(job=) to keep waiting rather than starting again. A bad adsk.cam call can crash Fusion: if status reports last_crash, do not repeat that call unchanged.

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": "cam_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobNo
setupNo
targetsNo
timeout_sNo
allow_user_documentNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so well: it discloses the async/polling model, that generation continues server-side after timeout, the job-resumption contract, and a genuine hazard warning ('A bad adsk.cam call can crash Fusion... if status reports last_crash, do not repeat that call unchanged'). This is exactly the non-obvious context an agent needs before invoking.

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?

Content is front-loaded — the core action and return values come first, then targets defaults, then background/timeout behavior, then the crash caveat. Sentences are dense but each earns its place; the only weakness is ragged line wrapping that splits sentences mid-clause.

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 long-running, background-executing, potentially crash-inducing tool, the description covers the lifecycle (start, poll, timeout, resume) and return contract, and an output schema exists so return field details need not be spelled out. The gaps are the undefined 'setup' and 'allow_user_document' parameters and no stated precondition for when generation is even applicable.

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 description coverage is 0% across 5 parameters, so the description must compensate. It meaningfully explains 'targets' (setup or operation names, default all operations of the last setup), 'job' (resumption id), and 'timeout_s' (wait duration after which generation continues), but leaves 'setup' and 'allow_user_document' entirely undefined — the latter is a boolean that plausibly gates a risky behavior and deserves a sentence.

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+resource ('Generate toolpaths') and states what the call returns (per-operation toolpath validity, checkToolpath result, all_valid). It is clearly separable from mutation siblings like cam_add_operation or cam_create_setup, though it never names an alternative explicitly.

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 concrete operational guidance: targets default to all operations of the last setup, generation runs in the background while the tool polls, and on timeout the agent should resume with cam_generate(job=<id>) rather than restarting. It stops short of naming when to use a sibling instead (e.g., a post-processing or validation-only tool).

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