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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds behavior the annotations cannot: it is a non-blocking snapshot, polling is wrong, and the status lifecycle is enumerated (queued/processing/succeeded/failed with url vs error.message). It even specifies the intended reporting behavior for the result.

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 core definition, then WHEN, then OUTPUT — a clean triage order with almost no waste. The all-caps labels (SINGLE, IMMEDIATE, WHEN, OUTPUT) are slightly stylized, but each sentence carries distinct 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 single-param read with no output schema, the description covers the gaps that matter: that it does not block, the full status enumeration with what url and error.message mean, and how the result should be surfaced to the user. Nothing an agent needs in order to call and interpret it is missing.

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?

There is only one parameter, and the schema already documents it fully (the job id returned by generate_audio) at 100% coverage, so the description correctly need not repeat it. It adds no format, source, or lookup guidance beyond the schema, which is the baseline-3 case.

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: reading ONE audio job's current state, plus the key property that it waits for nothing. It also explicitly distinguishes itself from wait_for_generation, generate_audio, and show_generation, so an agent can pick it without opening siblings' schemas.

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 an explicit WHEN scope (one job's raw fields now: cost, refund, failure reason), names the three alternatives and the conditions that select them, and adds a hard exclusion: 'Do not poll it.' Nothing about routing is left to inference.

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