Skip to main content
Glama
maximedns5

freecad-mcp

by maximedns5

begin_build

Start tracking a multi-part build by declaring expected components and checking for similar prior examples before creating geometry.

Instructions

Start tracking a non-trivial build, and check for similar prior examples.

Call this FIRST for anything beyond a single simple part — a multi-part
assembly (a chair, an enclosure with hardware, anything with more than
one body) — before creating any geometry. State the request in `prompt`
(as close to verbatim as you can) and list the components you expect to
build in `expected_components` (e.g. ["seat", "leg_fl", "leg_fr",
"leg_bl", "leg_br", "stretcher_front", ...]).

This does two things: it forces an explicit decomposition up front
(plan-shape mistakes — building a "chair" from 2 components instead of
9 — are much easier to avoid by committing to a component list before
building than to catch after), and it returns any similar builds already
verified in this project's corpus, which you should use as a reference
for tool sequence and structure, not copy blindly.

Always follow up with finish_build once you've built (and separately
verified with measure/probe_material_at) the components you declared
here — only builds that are re-verified as valid AND match this
declared component count get saved as reusable examples.

Args:
    doc_name: The document this build is happening in.
    prompt: The request you're building, close to verbatim.
    expected_components: Names you expect to create for this build.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYes
doc_nameYes
expected_componentsYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

With no annotations, the description carries the full behavioral burden. It explains that the tool 'forces an explicit decomposition up front' and 'returns any similar builds already verified,' implying a state-tracking and query operation. It notably says 'before creating any geometry,' signaling non-destructive scope. However, it doesn't explicitly state whether the tool modifies the document or session state beyond tracking.

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?

The description is front-loaded with a clear summary, then uses paragraphs and a list for args. While longer than average, every sentence earns its place (usage, rationale, follow-up, args). The rationale about plan-shape mistakes adds value but could be tightened slightly without losing impact.

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?

Given its complexity (prerequisites, follow-up, two actions), the description covers when, how, and why to call it, plus parameter details. It doesn't describe return values, but an output schema exists. It omits edge cases like error handling or behavior when no similar builds are found, but overall the description is sufficient for correct invocation.

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 description fully compensates for 0% schema coverage. It defines each parameter: doc_name as 'the document this build is happening in,' prompt as 'close to verbatim,' and expected_components with an example component list. It also explains how prompt and expected_components should be used, adding meaning well beyond raw schema.

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 opens with a specific verb+resource: 'Start tracking a non-trivial build, and check for similar prior examples.' It clearly distinguishes itself from siblings by positioning as the FIRST step for multi-part assemblies and referencing finish_build as the follow-up.

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

Usage Guidelines5/5

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

Provides explicit when-to-use: 'Call this FIRST for anything beyond a single simple part... before creating any geometry.' It also states the mandatory follow-up with finish_build, giving a clear usage workflow and distinguishing from one-shot build tools.

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/maximedns5/freecad-mcp'

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