Skip to main content
Glama
danielproxd2

MCP_CAD

by danielproxd2

record_batch_job

Record a batch operation on a set of files and return a dry-run preview of changes for human approval before execution.

Instructions

Registra un BatchJob (UN verbo determinista sobre un conjunto de archivos) y devuelve una VISTA PREVIA EN SECO (old→new por archivo) SIN mutar nada — esa vista previa ES la aprobación humana a escala (no se aprueban 70k archivos uno por uno; se aprueba verbo + alcance + el diff). Revísala; luego ejecútalo con run_batch_job.

Args: intent: Una oración: ¿qué cambio masivo es? fileset: {root, glob?, recurse?, paths?, exclude?, confidence?} — la carpeta (+filtro) o una lista explícita de rutas. Resolver el alcance lee SOLO metadatos de ruta; la geometría no se transmite. operation: {verb, params} — verb ∈ set_custom_property / export_document / force_rebuild / check_interference / get_bom. Ej: {"verb":"set_custom_property", "params":{"name":"Proveedor","value":"ACME","config":""}}. save_after: guardar cada archivo tras un verbo que modifica el documento (p.ej. set_custom_property). export/health/BOM no guardan el origen. continue_on_error: True → un archivo malo no aborta el lote (cada salto se reporta en el manifiesto). out_dir: carpeta ÚNICA para las salidas (export/BOM) y el manifiesto ("" = junto al origen). Una ruta de red aquí dispara una advertencia (la geometría no debe salir del host). confidence: 0–10 del plan (afecta go_recommendation: <6 → handback). preview_cap: máximo de filas en la vista previa.

Devuelve {batch_job_id, matched_files, preview, preview_truncated, warnings, go_recommendation}. [en: Record a batch job + return a dry-run preview — advisory only; review, then run_batch_job.]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intentYes
filesetYes
out_dirNo
operationYes
confidenceNo
save_afterNo
preview_capNo
continue_on_errorNo
Behavior5/5

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

With no annotations, the description carries full burden. It explains no mutation, dry-run only, advisory recommendations, metadata-only reading, network path warnings, and confidence affecting go_recommendation. Fully transparent.

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?

Well-structured with bullet-point Arg list, but slightly verbose with explanatory prose. Still front-loaded and every sentence adds value.

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 complexity (8 params, nested objects, no output schema), the description covers purpose, parameters, return fields, usage flow, and limitations. Extremely complete.

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 explanations for all 8 parameters, including examples for 'operation' and semantics for 'fileset'. Adds immense value beyond 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 clearly states the tool records a batch job and returns a dry-run preview without mutation. It uses specific verbs ('Registra...devuelve...SIN mutar') and distinguishes from the sibling 'run_batch_job'.

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?

Explicitly guides use: first use this tool for advisorial preview, then use 'run_batch_job' to execute. It lacks explicit 'when not to use' but context is clear.

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/solidworks-mcp'

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