Skip to main content
Glama

run_batch_job

Execute a recorded batch job file by file, with complete manifest and skips reported. Requires human approval and supports overrides for low confidence or warnings.

Instructions

Ejecuta un BatchJob registrado: aplica el verbo archivo POR archivo, con recibo por archivo (abierto/op/guardado/cerrado) y un MANIFIESTO COMPLETO — cada archivo saltado se reporta (truncar en silencio es el pecado capital).

ESTA llamada (aprobada en el cliente MCP) es la aprobación humana del lote.

Compuertas (tres niveles, como run_assembly_plan):

  1. go_recommendation='partial_or_handback' bloquea salvo override_low_confidence=True;

  2. advertencias 'risky' (irreversible-sin-guardar / ruta de red) bloquean salvo override_warnings=True (flag INDEPENDIENTE — forzar una no desactiva la otra);

  3. fileset vacío o '' sin resolver → se RECHAZA SIEMPRE. No borra archivos (borrado diferido por diseño). Devuelve {ok, changed, skipped, inspected, failed, manifest, failures, log_path} (los verbos de solo-lectura — rebuild/interference/BOM — cuentan como 'inspected', no 'skipped'). [en: Execute a recorded batch job file by file; complete manifest, every skip reported; read-only verbs counted as 'inspected'; no deletion.]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
batch_job_idYes
override_warningsNo
override_low_confidenceNo
Behavior5/5

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

No annotations provided, but description thoroughly discloses file-by-file execution, reporting of skipped files, return object keys (ok, changed, skipped, inspected, failed, manifest, failures, log_path), read-only verbs counted as 'inspected', and no deletion (deferred deletion). All behavioral traits are 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?

Description is somewhat lengthy due to bilingual content and detailed gate explanation, but it is well-structured with numbered gates and front-loads the main action. Could be tighter without losing clarity.

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?

Covers overall behavior, return value keys, and gates adequately. Given no output schema, description provides necessary details but could elaborate on error cases (e.g., missing batch_job_id) or edge cases.

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?

Schema has 0% description coverage, but description explains all three parameters: batch_job_id (implied the recorded batch job), override_warnings (gate 2 override for risky warnings), and override_low_confidence (gate 1 override). Adds essential meaning 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?

Description clearly states 'Ejecuta un BatchJob registrado' (execute a recorded batch job) with specific verb and resource. It distinguishes from siblings like run_assembly_plan, run_feature_plan, and run_macro_job by emphasizing file-by-file application, complete manifest, and human approval step.

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?

Description explicitly positions this as the human approval step and outlines three gate levels with conditions for override. It lacks explicit 'when not to use' but provides sufficient context via gates and references similar tool run_assembly_plan.

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