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

Annotations already declare readOnlyHint=false / destructiveHint=true / idempotentHint=false, and the description goes well beyond them: a 25s per-call wait, a one-time handover that 'reads as expired' on re-ask, and 1–4 minute run durations. This is precisely the mutation/lifecycle context an agent needs and cannot get from the schema.

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?

Front-loaded with the tool's identity, then each sentence carries distinct operational information (wait time, polling loop, one-time retrieval, cancellation). No filler sentences and nothing repeated from the schema verbatim.

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?

With no output schema, the description still tells the agent what comes back ('returns it or says it is still writing and for how long') and warns about the expiry semantics. For a non-idempotent polling tool this is complete enough to call correctly without trial and error.

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 100%, so both parameters are already documented in structured data and the baseline is 3. The description reinforces the meaning of cancel ('stop a run') and implies jobId comes from draft_reply, but adds no syntax or value details the schema lacks.

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?

Opens with a specific verb+resource ('Picks up the result of draft_reply') and explicitly anchors itself to the sibling draft_reply, so an agent can separate the drafting tool from the collection tool immediately. The 25-second wait and polling behavior further pin down what the tool actually does.

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?

Gives explicit operational guidance: 'Keep calling until it returns: runs take 1 to 4 minutes,' plus the escape hatch 'Pass cancel:true to stop a run you no longer want.' This tells the agent both the loop pattern and when not to collect, which is exactly what alternatives guidance looks like.

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