Skip to main content
Glama

run_macro_job

Execute a recorded macro job on the host: create temp .swb, run via RunMacro2, rebuild, delete temp. Network egress blocked; warnings overrideable; audit logged.

Instructions

Ejecuta un MacroJob registrado: materializa la fuente en un .swb temporal EN EL HOST, lo corre vía RunMacro2 (UserControl=False), reconstruye y borra el temporal. Ejecuta VBA arbitraria (cruza la restricción #2). ESTA llamada (aprobada en el cliente MCP) es la aprobación humana.

Compuertas (cuatro niveles): 0) señales de EGRESO a la red (HTTP/stream/descarga/UNC) → restricción #1, RECHAZO NO ANULABLE (la geometría no sale del host — #1 no está waived, a diferencia de #2);

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

  2. advertencias 'risky' (siempre incluyen la nota de #2; más señales de sistema de archivos/shell) bloquean salvo override_warnings=True (flag independiente);

  3. '' sin resolver en el código → se RECHAZA SIEMPRE. La fuente que corre se anexa a un log de auditoría en el host (MCP_CAD_MACRO_AUDIT_LOG). El .swb nunca sale del host (VBA es texto). Devuelve {ok, ran, run_error, rebuilt, audit_log, audit_recorded}. [en: Execute a recorded macro job — temp .swb on-host, RunMacro2, rebuild, delete temp; network-egress is a hard non-overridable block (constraint #1); source appended to the on-host audit log.]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
macro_job_idYes
override_warningsNo
override_low_confidenceNo
Behavior5/5

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

Given no annotations, description fully discloses creation of temp .swb, RunMacro2 execution, network egress block, audit logging, and return fields. Also explains four levels of gating with override conditions.

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

Conciseness3/5

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

Description is long and mixes bilingual text, purpose, process, and restrictions in a dense block. While front-loaded with purpose, it could be more concise and better structured.

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 the full workflow, restrictions, audit log, and return format. Missing explicit parameter details and potential error handling, but sufficient for understanding execution and outcomes.

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 coverage is 0%, but description indirectly explains override_warnings and override_low_confidence via gate rules. macro_job_id is not explicitly described, though its purpose is clear from context.

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?

Clearly states 'Ejecuta un MacroJob registrado' and describes the process of materializing, running, and cleaning up. Distinguishes from sibling run tools by focusing on macro jobs with VBA execution.

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?

Mentions that this call represents human approval and details gate conditions, but does not explicitly compare to alternatives like run_assembly_plan or run_batch_job. Usage context is implied rather than explicit.

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