Skip to main content
Glama

await_subtasks

Wait for a batch of subtasks to finish and return each child's state, summary, changed files and merge status, so you can decide whether to keep polling, retry failures, or continue.

Instructions

Wait for your latest subtask batch (default 30 seconds, at most 120). Returns child states, scrubbed summaries, changed files and merge status. ready: true means every child merged and the runner brought integration into your worktree. When children are still running, call again. Failed or cancelled children are reported for you to retry with new ids or escalate.

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>"
    },
    "name": "await_subtasks"
  }
}

Input Schema

NameRequiredDescriptionDefault
timeout_sNo
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

A4.1/5.0
Behavior4/5

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

Annotations only say non-read-only, non-destructive, non-idempotent; the description adds real context the agent could not infer: a 30s default with 120s cap, the meaning of ready:true, and the fact that the runner merges integration into the caller's worktree. That last point is a meaningful side effect worth disclosing. It does not cover timeout-expiry behavior or auth/rate considerations beyond the token pattern.

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 tight sentences, each carrying distinct information (timeout, return payload, ready semantics, retry path), with the core action front-loaded. No filler or restatement of the tool name.

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?

With no output schema, the description correctly shoulders the burden by enumerating the return payload and the ready flag. The main remaining gap is what a timed-out wait returns (partial states vs. empty) and whether the batch is consumed by a call, which matters for a wait/poll tool.

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 67%, with timeout_s carrying only min/max bounds and no prose; the description supplies the missing default (30s) and confirms the 120s ceiling, which is genuine added meaning. execution_id and agent_token are already documented in the schema, so no further value is needed there.

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?

"Wait for your latest subtask batch" states a specific verb (wait) and resource (subtask batch) and immediately lists what comes back (child states, summaries, changed files, merge status). It is clearly distinct from spawn_subtasks or execution_status in intent, though it never names an alternative 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 gives concrete re-invocation guidance ("When children are still running, call again") and a follow-up path for failures ("retry with new ids or escalate"), naming the escalate sibling. It stops short of saying when NOT to use it or how it differs from a plain execution-status poll.

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