Skip to main content
Glama
communitycad-mcp

communitycad-mcp

Official

Search models

search_models
Read-only

Find and filter CommunityCAD's public CAD models by query, tags, dimensions, creator, company, file type, license, or printability; returns compact cards with IDs and page URLs.

Instructions

Search CommunityCAD's public models. Returns compact cards with IDs and page URLs. Size filters leave out models whose size is unknown.

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": "search_models"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNorelevance
tagsNoModels with all of these tags.
limitNo
queryNoWhat to look for, e.g. '24V enclosed power supply'.
offsetNo
companyNoA company's slug.
creatorNoA creator's username.
max_x_mmNoMust fit within this X (X and Y may swap).
max_y_mmNoMust fit within this Y (X and Y may swap).
max_z_mmNoMust fit within this height.
semanticNoRank by meaning instead of keywords. Needs a query; sort must be relevance.
file_typesNoModels offering any of these, e.g. ['step', 'stl'].
has_cad_sourceNoTrue: only models with STEP, IGES or a native CAD file.
license_familyNopermissive (CC0, MIT...), attribution (CC BY), share_alike (CC BY-SA, GPL...), non_commercial, other.
printable_onlyNoOnly models with STL/3MF/OBJ files.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), so the description's added value is the return shape and the genuine caveat that size filters silently exclude models with unknown dimensions. That caveat is a real behavioral disclosure, but pagination behavior, default result ordering, and result caps are left unaddressed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler, and the primary purpose is front-loaded ahead of the return-shape detail and the filter caveat. Every sentence carries distinct information.

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?

For a 15-parameter search tool with no output schema, the description gives useful partial coverage of the return value and one important filter caveat. It omits how to page through results beyond offset, what the compact card contains, and how to escalate to a full model fetch, which an agent would need to chain calls correctly.

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 80%, so the schema already explains most parameters, including semantic ranking constraints and license families. The description adds meaning only for the size filters (max_x/y/z), noting the unknown-size exclusion; it says nothing extra about query, tags, or sort semantics. Baseline 3 applies.

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 (search CommunityCAD's public models) and describes the result shape (compact cards with IDs and page URLs), which implicitly separates it from detail-fetching siblings like get_model. It stops short of naming that sibling explicitly, so the differentiation is inferred rather than stated.

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 by the scope phrase 'public models' and by the note that results are compact cards, hinting that a follow-up detail call is needed. There is no explicit when-to-use vs. when-not guidance and no named alternative for retrieving full model details.

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