Skip to main content
Glama

body_task_start

Start a long-running batch in the background and receive a task ID immediately, so agents can continue working while polling status or cancelling the task later.

Instructions

Start a LONG batch in the background and get a task id straight away.

The agent keeps working while the body carries on (own isolated context, never the page you are using). Poll body_task_status(task_id) for progress, or body_task_cancel(task_id) to stop it. Small jobs should just use hands_batch - this is for the slow ones.

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": {
      "actions": "<actions>"
    },
    "name": "body_task_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses asynchronous background execution, returns a task id immediately, runs in its own isolated context, and explicitly does not touch the page the agent is using. It stops short of covering failure behavior, concurrency limits, or what happens if the batch errors, so it is strong but not exhaustive.

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?

Four short sentences with the core promise front-loaded, then context, then lifecycle pointers, then the routing rule away to hands_batch. Every sentence earns its place and nothing is repeated from structured fields.

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?

For a fire-and-forget launcher with no output schema, the description correctly explains what comes back (a task id) and how to follow up, which is the information an agent actually needs. The one real gap is the undocumented 'actions' payload, which matters because it is required and free-form.

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

Parameters2/5

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

There is one required parameter, 'actions', an array of free-form objects with additionalProperties=true and 0% schema description coverage, and the description never mentions it, its item shape, or any examples. All the description's detail is about lifecycle and returns, none about the sole input, so the agent is left guessing at payload structure.

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?

States a specific verb ('Start') plus the resource ('a LONG batch') and the immediate outcome ('get a task id straight away'), which is precisely what differentiates it from the sibling body_task_status and body_task_cancel tools. An agent can tell this is the launcher, not the poller, without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit positive condition ('LONG batch', 'the slow ones') and an explicit negative one with a named alternative ('Small jobs should just use hands_batch'). It also routes follow-up actions to body_task_status for progress and body_task_cancel to stop, so the whole when/when-not/alternative triad is covered.

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