Skip to main content
Glama
fusion-cam

fusion-cam

cam_create_setup

Creates a milling setup in Fusion with configurable stock offset and WCS origin, returning stock box and WCS coordinates in millimeters for CAM programming.

Instructions

Create a milling setup on the scratch document (opens the Manufacture workspace). Units mm.

stock_offset_mm: relative-box stock, a number (sides and top; bottom 0) or {"sides", "top", "bottom"}. wcs: stock box point: 'top-centre' (default), 'top-corner-1'..'top-corner-4' (1=-X-Y, 2=+X-Y, 3=-X+Y, 4=+X+Y), 'centre', 'bottom-centre', 'bottom-corner-N'; prefix 'model-' for the model box instead; or 'model-origin'. body: body name or index (default: all solid bodies). Returns the stock box in world mm and in WCS mm and the WCS origin in world mm. Refuses on documents not created by import_step unless allow_user_document=true, and while Fusion is mid-command.

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_create_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
wcsNotop-centre
bodyNo
nameNo
timeout_sNo
stock_offset_mmNo
allow_user_documentNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the disclosure burden and does well: it names the workspace side effect, declares units (mm), documents two distinct refusal conditions (non-import_step documents, mid-command state), and explains the return payload (stock box in world and WCS mm plus WCS origin). It does not state that a setup is written to the document or what happens on a name collision, so it falls short of fully covering mutation behavior.

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 workspace side effect are front-loaded, followed by a dense but well-labelled parameter block, then return values and refusals. Nearly every clause carries information; the long wcs enumeration is necessary given the 0% schema coverage.

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?

An output schema exists, yet the description still summarizes the return payload, and it adds units, side effects, and refusal conditions, which is strong coverage for a 6-parameter mutation tool. Remaining gaps are idempotency (existing setup with the same name) and the meaning of timeout_s, both of which matter for an agent driving Fusion in an automation loop.

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?

Schema coverage is 0%, and the description compensates thoroughly: wcs is enumerated with corner numbering decoded (1=-X-Y, 2=+X-Y...) plus the 'model-' prefix and 'model-origin' alternative; stock_offset_mm is explained as sides/top with bottom fixed at 0 and the dict form given; body is defined as name or index with an all-bodies default. Only name and timeout_s go unmentioned, and both are largely self-evident.

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?

States a specific verb and resource ('Create a milling setup') plus a scope constraint ('on the scratch document') and a side effect ('opens the Manufacture workspace'). The scratch-document scoping implicitly separates it from import_step (which produces the document) and cam_add_operation (which consumes the setup), though no sibling is named directly.

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?

Usage is implied rather than stated: the refusal clause 'Refuses on documents not created by import_step unless allow_user_document=true' tells the agent import_step is the normal predecessor, and the mid-command refusal gives an operational precondition. There is no explicit when-to-use vs alternative guidance and no mention of cam_add_operation as the follow-up step.

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