Skip to main content
Glama

search_part_catalog

Search open CAD catalogs for standard parts by abstracted specifications and receive ranked candidates with fit judgment, deep-links, and insert-or-macro recommendations.

Instructions

Busca una pieza ESTÁNDAR en catálogos abiertos y juzga su ajuste (search+judge).

Lane de reúso open-resource (docs/OPEN_RESOURCE_LANE.md). Cuando el diseñador pide una pieza estándar (tornillo, tuerca, balero, brida, perfil, conector…) que NO hace falta modelar de cero, resuelve la intención abstracta en candidatos rankeados de 3D ContentCentral / McMaster-Carr / TraceParts — cada uno con su deep-link, formatos, licencia, veredicto nativo-vs-tonto y recomendación insertar-vs-macro.

Modo v1 = DEEP-LINK: NO descarga geometría. Devuelve una URL de búsqueda por recurso; el diseñador descarga el archivo EN SU MÁQUINA. Luego: insertar+matear (place_and_mate / stack_components); si es NATIVA parametrica → editar cotas (list_dimensions / modify_dimension); si es sólido tonto (lo usual en catálogos) y hay que cambiar medidas → regenerar equivalente parametrico con la lane de macros (record_macro_job / run_macro_job).

Constraint #1: SÓLO texto abstracto (tipo, estándar, medida nominal, material) se vuelve consulta saliente — nunca geometría del cliente. Nada de terceros entra al repo; la geometría descargada se queda en el host.

[en: Search open CAD resources for a STANDARD part from abstracted text intent and judge fit (folds search + judge). v1 DEEP-LINK mode downloads NOTHING — it returns ranked candidates with a per-resource search URL, license, native-vs-dumb verdict, and an insert-vs-macro recommendation. The designer fetches the file onto their own machine; the existing geometry tools take over. Only abstracted text leaves the host.]

Args: spec: Structured ABSTRACTED part spec — generic fields only: type ("tuerca hexagonal"), standard ("DIN 934"), size ("M8x1.25"), material ("acero inoxidable A2"), nominal ({dim: value}, echoed back), query (explicit override). Never put customer geometry here. resources: subset of ["3dcontentcentral","mcmaster","traceparts"] (default all; unknown names ignored). top_n: max candidates (default 3). needs_edit: True if the designer will change dimensions — drives the insert-vs-macro recommendation (a dumb catalog .sldprt → macro lane).

Returns: {"query": str, "needs_edit": bool, "count": int, "note": str, "candidates": [{"resource","title","standard","part_number","nominal", "formats","native_vs_dumb","license_class","deep_link","deep_link_note", "fit_verdict","fit_score","recommendation"}, ...]} # ranked by fit_score

Reúso-primero: si hay una carpeta indexada localmente, llama PRIMERO a query_part_library; usa esta herramienta cuando NO exista local y convenga traer un estándar del catálogo abierto.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
specYes
top_nNo
resourcesNo
needs_editNo
Behavior5/5

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

With no annotations, the description fully discloses behavior: it does not download geometry, returns URLs and rankings, and provides fit verdicts and recommendations. It also explains follow-up actions (insert, edit, macro) and privacy constraints.

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 well-structured with sections but includes both Spanish and English versions, making it longer than necessary. Each sentence adds value, but the duplication reduces conciseness slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity and no output schema, the description covers purpose, parameters, return structure, usage guidelines, constraints, and alternative tools. It also explains post-search actions, making it comprehensive.

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?

Despite 0% schema coverage, the description provides detailed parameter documentation: spec includes type, standard, size, material, nominal, query; resources lists allowed values; top_n and needs_edit have defaults and explanations. This adds value beyond the plain 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 explicitly states the tool searches for standard parts in open catalogs and judges fit, distinguishing it from the sibling query_part_library. It provides specific examples of parts (tornillo, tuerca, etc.) and the mode of operation (deep-link).

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?

The description gives clear when-to-use guidance: only when local library lacks the part and it's a standard. It names the alternative query_part_library and states constraints like abstracted text only, no customer geometry.

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/danielproxd2/MCP_CAD'

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