native_subagent_completed

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is covered and the description's "Persist" is consistent with a write. Beyond that it adds almost nothing behavioral: no idempotency semantics (what happens if the same task_id/lease_id is persisted twice), no statement of which status values are terminal, and no error-path behavior despite an `error` parameter existing.

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?

A single front-loaded sentence with no filler, and the action verb leads. The only cost is the reference to a non-sibling tool name ("wait_threads"), which spends words on a pointer the agent cannot follow.

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?

This is a state-mutating persistence tool with 5 parameters, zero schema descriptions, a nested object parameter, and no output schema. One sentence cannot cover how task_id/lease_id are obtained, whether persistence is mandatory per subagent, or how it interacts with native_subagent_started/event — all of which an agent needs to call it correctly.

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 description coverage is 0% across 5 parameters, so the description must compensate and it does not. Only "result" and "status" are obliquely implied by "terminal result"; task_id, lease_id, and error are never explained, and the completed/failed/cancelled/blocked enum meanings are left entirely undefined.

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?

States a specific verb ("Persist") and a specific resource ("the terminal result returned by a native Codex subagent"), which distinguishes it from the streaming-style sibling native_subagent_event. However, it never contrasts itself with native_subagent_started/native_subagent_event explicitly, and it references "wait_threads," a tool that is not among the listed siblings (wait_tasks is), which muddies the picture.

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?

The phrase "after wait_threads completes" implies a trigger condition, so timing is at least hinted at. But there is no explicit when-not guidance, no statement that non-terminal progress should go to native_subagent_event instead, and no mention of prerequisites such as holding a valid lease_id.

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