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

Annotations declare non-idempotent/destructive, and the description explains exactly why: the result is handed over ONCE and re-asking after collection 'reads as expired'. It also discloses the 25-second blocking wait and the cancel semantics, which the annotations alone cannot convey.

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?

Four tight sentences, front-loaded with the core action, then timing, then the one-time-consumption caveat, then the cancel escape hatch. No filler; every sentence changes how an agent would call it.

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?

Despite no output schema, the description explains what comes back ('returns it or says it is still writing and for how long') and the full lifecycle including expiry. An agent has everything needed to drive the polling loop 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: jobId is the value returned by draft_reply, and cancel:true stops a run rather than collecting it. This goes beyond the terse schema text.

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+resource ('Picks up the result of draft_reply') and immediately ties it to the sibling that produces the draft. An agent can distinguish this collector from draft_reply itself without opening either schema.

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?

Explicitly describes the polling pattern ('Keep calling until it returns'), gives the timing envelope ('runs take 1 to 4 minutes', 25s per call wait), and provides an alternative path ('Pass cancel:true to stop a run'). When-to-use, how-long, and how-to-abort are all covered.

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