Resume subagent

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

With no annotations, the description carries the full burden and does so: blocking semantics, Codex uncached full-thread replay, a warning in the result, idle-time refusal (default 30 minutes, configurable via codexResumeIdleSeconds in models.yaml), the allow_expensive_resume escape hatch, and single-slot message queuing. These are exactly the non-obvious traits an agent needs before invoking a costly operation.

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

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

It is dense but front-loaded: the core action and its blocking nature come first, followed by the Codex caveats and then the queuing fallback. A few clauses are packed tightly, but every sentence carries operational information.

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

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

For a 6-parameter mutation-like tool with no annotations and no output schema, the description covers the major risks (cost, refusal, blocking, queuing) thoroughly. It leaves run_in_background and effort unexplained, which is a modest gap given the otherwise rich behavioral detail.

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

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

Schema coverage is 67%, so the schema already documents agent, effort, timeout, and allow_expensive_resume. The description adds real context only for the idle-limit default behind allow_expensive_resume and restates timeout's echo behavior. It says nothing about effort or run_in_background, leaving those to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Resume a completed agent by ID or name, preserving its full history.' This is much clearer than the ambiguous tool name send_message / title 'Resume subagent', and it explains the mid-turn queuing case. It compares itself to spawn_agent ('Blocks like spawn_agent') but only for behavior, not to differentiate when to choose one over the other.

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

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

It clearly frames the two usage modes: resuming a completed agent, and queuing a message when the agent is mid-turn, and it names list_agents/get_agent_events as the way to check delivery. It never explicitly says when to prefer spawn_agent over this tool, so the guidance is strong but not exhaustive.

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