Skip to main content
Glama
fusion-cam

fusion-cam

cam_list_tools

Find cutting tools by type, diameter, or text and return IDs for cam_add_operation; choose bundled samples, cloud, or a Fusion-exported JSON library.

Instructions

Find cutting tools; diameters in mm. Returns tool ids for cam_add_operation.

source: 'samples' (Fusion's bundled libraries, e.g. 'Milling Tools (Metric)', 'Hole Making Tools (Metric)', 'Tutorial Tools (Metric)'; call with no filters to list them), a path to a tool library .json exported from Fusion, or 'cloud' (Fusion's online library: slow, about 8 s, and implicated in a Fusion crash in Phase 0, so only when the user asks). type: e.g. 'flat end mill', 'face mill', 'drill', 'spot drill', 'tap right hand', 'chamfer mill'. text filters the description. The sample tools carry generic feeds/speeds presets (e.g. S5000 F1000): review them before real machining.

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_list_tools"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNo
typeNo
limitNo
sourceNosamples
libraryNo
timeout_sNo
diameter_max_mmNo
diameter_min_mmNo

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 present, the description carries the full burden and does well: it discloses latency (~8 s), a crash risk tied to the cloud source, unit conventions (mm), and a data-quality caveat that sample tools carry generic feeds/speeds presets to review before real machining. It does not cover pagination behavior, network requirements for .json paths, or what happens when filters match 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?

Front-loaded with the core purpose and return value in one line, then parameter guidance. The parenthetical example lists for source and type are dense but earn their place as concrete vocabulary the agent would not otherwise know. Slightly long, but no sentence is pure filler.

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 return-value explanation is rightly omitted, and the safety/latency warnings are a genuine addition. However, for an 8-parameter tool with zero schema descriptions, leaving limit, timeout, diameter bounds, and library semantics undefined means an agent cannot set those parameters confidently.

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%, so the description must compensate for 8 parameters and only partially does: 'text', 'type' (with concrete examples like 'flat end mill', 'face mill', 'tap right hand') and source values are explained. 'limit', 'timeout_s', 'diameter_min_mm'/'diameter_max_mm', and 'library' are not addressed — and the relationship between the 'library' parameter and the 'path to a tool library .json' source value is left ambiguous.

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?

States a specific verb and resource ('Find cutting tools'), clarifies units ('diameters in mm'), and names the downstream consumer of the result ('Returns tool ids for cam_add_operation'). An agent can tell immediately this is a discovery/listing tool distinct from action-oriented siblings like cam_add_operation or cam_generate.

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?

Gives explicit conditional guidance for the riskiest option: 'cloud' is slow (~8 s) and implicated in a crash, 'so only when the user asks.' It also says to call with no filters to list the bundled libraries, which is a concrete usage instruction. It stops short of naming an alternative tool for tool discovery, so it is not a full when/when-not/alternatives treatment.

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