Nanites

Start Sub-Agent Job

start_sub_agent_job

Start a sub-agent job asynchronously, receive its job ID immediately, and avoid blocking on long or heavy model calls. Poll status to retrieve results.

Instructions

Queue a sub-agent job on the profile's async job FIFO and return its job_id immediately (non-blocking — for long-horizon work on slow/big models instead of a tool call that blocks for minutes). Same validated inputs as run_sub_agent; when the profile's concurrency tier is at capacity the job waits queued rather than erroring. Poll with get_sub_agent_job_status.

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": {
      "profile": "<profile>",
      "brief": "<brief>"
    },
    "name": "start_sub_agent_job"
  }
}

Input Schema

Name	Required	Description	Default
`task`	No
`brief`	Yes
`roles`	No
`effort`	No
`profile`	Yes
`model_id`	No
`provider`	No
`output_schema`	No
`output_schema_name`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 27, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden, and it delivers the key async traits: non-blocking, FIFO ordering, queued-when-at-capacity rather than erroring, and same validation as run_sub_agent. It does not cover failure modes (e.g., invalid profile, job rejection) or persistence, which keeps it short of a 5.

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?

Three dense sentences with no filler: primary action and return, use case and capacity behavior, and polling instruction. The most decision-relevant facts (non-blocking, returns job_id) are front-loaded.

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 9-parameter tool with no annotations and no output schema, the description covers the action, return value, async semantics, concurrency-tier behavior, and follow-up polling — surprisingly complete on behavior. It falls short only on parameter definitions and error semantics, which are partially mitigated by the run_sub_agent reference.

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?

Schema description coverage is 0% across 9 parameters, so the description must compensate, but it only says 'Same validated inputs as run_sub_agent' — a delegation rather than an explanation of what each parameter means. The schema's names, types, and enums are all an agent has to go on for fields like task, roles, effort, output_schema, and provider.

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?

The description states a specific verb ('Queue'), a precise resource ('a sub-agent job on the profile's async job FIFO'), and the immediate return ('return its job_id immediately'). It explicitly contrasts with the blocking sibling run_sub_agent, so an agent can distinguish them without inspecting either 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?

Explicit when-to-use guidance is present: 'for long-horizon work on slow/big models instead of a tool call that blocks for minutes.' It names the alternative (run_sub_agent) for the blocking case and prescribes the follow-up tool ('Poll with get_sub_agent_job_status'), plus explains capacity behavior (waits queued rather than erroring).

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

Deploy Server