Skip to main content
Glama

spawn_subtasks

Delegate up to eight scoped subtasks when a frozen contract enables swarms; children inherit checks, use leased non-overlapping paths, and must finish before delegated paths are available.

Instructions

Delegate 1–8 subtasks through the runner when the frozen contract enables swarms. Child ids are namespaced under yours. Paths must be within your current leases and must not overlap siblings. Children inherit your checks; only siblings in this call may be dependencies. Delegated paths are unavailable to you until the children finish. Subtasks cannot delegate.

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": {
      "execution_id": "<execution_id>",
      "agent_token": "<agent_token>",
      "subtasks": "<subtasks>"
    },
    "name": "spawn_subtasks"
  }
}

Input Schema

NameRequiredDescriptionDefault
subtasksYes
agent_tokenYesThe agent token join_execution returned (once).
execution_idYesThe heads-down run (exe-…).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A4.2/5.0
Behavior4/5

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

Well beyond the annotations, the description discloses that delegated paths become unavailable to the caller until children finish, that children inherit your checks, and that ids are namespaced. With destructiveHint=false already covering safety, the remaining undisclosed trait is that idempotentHint=false means a repeat call spawns a second set of children — no warning about duplicate spawning is given.

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?

Six short sentences, each of which carries a distinct constraint: gating condition, namespacing, path rules, inheritance, dependency scoping, blocking semantics, and no recursion. No filler, and the enabling condition is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description never says what a successful call returns (presumably the spawned child ids) or what happens on partial failure when some paths overlap. For a non-idempotent mutation that blocks resources until children finish, that return/error contract should be stated.

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

Parameters5/5

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

At 67% schema coverage the description adds real meaning to three fields: `id` (namespaced under the parent's id), `paths` (must sit within current leases and must not overlap siblings), and `depends_on` (only siblings in this same call). The 1–8 bound on `subtasks` is also restated as an operational limit; only `instructions` is left to the schema.

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?

The description uses a concrete verb and resource plus scope: 'Delegate 1–8 subtasks through the runner when the frozen contract enables swarms', which immediately tells an agent this spawns child work items under a gate. It does not name any sibling (e.g. await_subtasks) or contrast itself with them, so an agent must infer the pairing rather than being routed explicitly.

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?

It states a clear enabling condition ('when the frozen contract enables swarms') and a hard exclusion ('Subtasks cannot delegate'), plus dependency scoping ('only siblings in this call may be dependencies'). What's missing is any explicit alternative or when-not guidance, e.g. when a child should instead be handled inline or how completion is awaited.

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