Skip to main content
Glama

Lanzar tarea de Copilot

create_agent_task

Launches a GitHub Copilot cloud agent task for a repository using a prompt and model, and lists accepted models if the requested model is rejected.

Instructions

Lanza una tarea del agente de Copilot en la nube. El modelo se envía tal cual. Si ese modelo ya se vio rechazado, no llama a la API y lista los modelos vistos aceptados.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "repo": "<repo>",
      "prompt": "<prompt>",
      "model": "<model>"
    },
    "name": "create_agent_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
repoYesRepositorio en la forma owner/name.
modelYesModelo. Se envía tal cual a la API, sin una lista cerrada.
promptYesInstrucción para el agente.
base_refNoRama base para la rama nueva o la pull request.
head_refNoRama existente. Con base_ref, el agente hace commit en esa rama.
custom_agentNoNombre del custom agent, sin la extensión.
create_pull_requestNoSi es true, la API abre una pull request.

Output Schema

NameRequiredDescriptionDefault
repoYes
stateYes
task_idYes
html_urlYes
created_atYes
requested_modelYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already disclose that this is a non-read-only, open-world, non-idempotent, non-destructive operation. Beyond that, the description adds real behavioral detail: the model string is passed through unvalidated, and a previously rejected model short-circuits the API call and returns the list of accepted models instead — a non-obvious control-flow behavior.

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?

Three short sentences, front-loaded with the action, followed by the two behavioral facts that matter. The second sentence largely restates the model parameter's schema description, so it is not perfectly waste-free, but overall it is tight and readable.

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?

An output schema exists, so return-value explanation is not required, and the description still flags the notable alternate outcome when a model is rejected. For a 7-parameter cloud task launcher, the main gap is the absence of any note on required repository or authentication access, which is left entirely to error handling.

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 100%, so every parameter including base_ref, head_ref, custom_agent, and create_pull_request is already documented. The description only reiterates that the model is sent as-is, which duplicates the schema's own wording for that parameter, so the baseline of 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 concrete verb and resource ('Lanza una tarea del agente de Copilot en la nube'), which clearly distinguishes creation from the get_agent_task and list_copilot_models siblings. It never names those siblings explicitly, but the action verb makes the distinction inferable.

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?

The description gives one useful conditional: if the model was previously rejected, it skips the API call and lists accepted models. However, it does not say when to use this versus get_agent_task (e.g., to poll status after launching) or when a task should not be launched, leaving usage context implied.

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