Skip to main content
Glama

agy_wait_agent

Read-only

Wait for spawned subagents to finish and retrieve completed results, streaming each as it completes or waiting for the full batch.

Instructions

Wait for one or more Antigravity subagents to finish (mirrors native Codex wait). Pass wait_for='any' to stream results as each agent finishes, or 'all' to wait for the full batch. Returns completed results, conversation_id, changed_files, scope_violations, branch, and still_running.

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": {
      "agent_ids": "<agent_ids>"
    },
    "name": "agy_wait_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
wait_forNoReturn as soon as 'any' agent completes or wait until 'all' complete.any
agent_idsYesList of agent_id values returned by agy_spawn_agent.
timeout_secNoMaximum seconds to wait in this call (default 180, max 840).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

readOnlyHint=true already covers the safety profile, and the description adds real value on top: it discloses streaming behavior for 'any' versus full-batch blocking for 'all', and enumerates the returned payload (conversation_id, changed_files, scope_violations, branch, still_running). It stops short of saying what happens when timeout_sec elapses — presumably a partial result with still_running populated — which is the one behavior an agent most needs before choosing a timeout.

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

Conciseness4/5

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

Three front-loaded sentences with no filler; the blocking/streaming distinction and the return payload come early. The wait_for sentence partly duplicates the enum description in the schema, so it is not maximally economical, but nothing is wasted.

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, naming the returned fields is exactly the right compensation, and the three parameters are covered either by the schema or the description. The remaining gap is timeout semantics — what the caller receives on expiry — which matters for a tool whose default wait is 180 seconds.

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

Parameters3/5

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

Schema description coverage is 100%, so all three parameters are already documented including the enum for wait_for. The description restates the any/all semantics in prose but adds no syntax, format, or edge-case detail (e.g. duplicate agent_ids, interaction between wait_for='all' and timeout_sec). Baseline 3 applies.

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 and resource ('Wait for one or more Antigravity subagents to finish') and implicitly distinguishes itself from siblings like agy_spawn_agent and agy_status by being the blocking join operation. An agent can tell what this does without opening the schema.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: you wait after spawning agents, and the wait_for choice is explained. However, it never says when NOT to use this versus polling with agy_status, nor any precondition that the agent_ids must come from a prior agy_spawn_agent call in the same session.

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