Skip to main content
Glama

Delegar tarefa a outro modelo

delegate_task
Read-only

Delegate tasks to different AI models. Use list_models to see available model IDs and send complete instructions for processing.

Instructions

Envia uma tarefa para outro modelo de IA processar e devolve a resposta dele. Use list_models para ver os ids válidos (ex.: 'codex', 'deepseek:deepseek-chat', 'lmstudio:qwen/qwen3.6-35b-a3b'). A resposta vem do modelo delegado — avalie criticamente antes de usar.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYesInstruções completas e autocontidas da tarefa, incluindo todo o contexto necessário — o modelo destino não vê esta conversa
modelYesId do modelo destino, no formato retornado por list_models (ex.: 'codex' ou 'deepseek:deepseek-chat')
effortNoEsforço de raciocínio: para o codex aceita 'low', 'medium', 'high' ou 'xhigh'; para provedores de API (z.ai, OpenRouter etc.) só funciona se o provedor tiver 'effortStyle' configurado no config/models.json — nesse caso, use o valor que aquele provedor aceitar
workdirNoVale para codex, gemini e glm-maos: pasta do projeto que o modelo pode LER (caminho absoluto). Para o gemini, requer o arquivo de permissões do agy configurado (senão, mande o contexto no texto)
Behavior4/5

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

Annotations mark readOnlyHint and openWorldHint, and the description confirms no side effects. It adds the behavioral note that the response comes from the delegated model and should be critically evaluated, providing useful context beyond annotations.

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

Conciseness5/5

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

Two sentences plus parameter context. Every sentence earns its place: purpose, usage hint, and caution. Front-loaded with the key action and result. No fluff.

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?

Given full schema coverage and no output schema, the description covers what the tool does, how to configure delegation, and potential pitfalls. It is sufficiently complete for an agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by clarifying that 'task' must be self-contained, detailing 'effort' values per provider, and specifying when 'workdir' applies (codex, gemini). This goes beyond schema descriptions.

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 the tool sends a task to another AI model and returns its response. It uses a specific verb ('Envia') and resource ('tarefa para outro modelo'), and the sibling 'list_models' is distinct, so purpose is unambiguous.

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 advises using list_models to find valid model IDs and cautions to critically evaluate the delegated model's response. However, it does not specify when not to use this tool, missing some exclusionary context.

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/dpmadsen/multimodels-mcp'

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