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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so 'Read-only: it never starts or changes a run' largely restates structured data. The description does add behavioral context about the response content (URLs for audio, images or video) and the 'when it is done' completion condition, which is modest added value on top of the annotations.

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?

Two tight sentences, the purpose front-loaded in the first clause and the safety guarantee second. No filler and nothing to trim.

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?

An output schema exists, so return-value detail is not strictly required, and annotations cover the safety profile, making the description nearly sufficient for a one-parameter tool. The only real gap is the unexplained project_id, which leaves a small hole for an otherwise simple tool.

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% for the single required project_id, and the description never mentions the parameter at all. With no compensation for the coverage gap, the agent gets no meaning beyond the bare property name and type.

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 ('check the progress of a run') and the payoff ('return the URLs of the finished files'), and implicitly separates itself from generate_result by noting it 'never starts or changes a run'. An agent can distinguish polling from generation 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?

Usage is only implied: the polling/progress framing suggests it is called after a run has been started, and the 'never starts or changes a run' clause hints that generate_result is the starter. But no sibling is named and there is no explicit when-to-use, when-not-to-use, or polling-cadence guidance.

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