estimate translated audio preview

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

Annotations already declare readOnly/idempotent/non-destructive, and the description partly restates that ('does not translate, create a job, trim or modify the audio'), but it adds real context annotations cannot carry: no provider charges, the free-plan limitSeconds bound, that only a bounded part is quoted, and that create refuses over-limit sources rather than trimming them. The 'external' billing meaning is also explained. Good depth, with a little redundancy against 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?

Front-loaded with purpose and the alternative, then the read-only guarantee, then the returned fields, then the duration-limit edge case. Dense but every paragraph carries distinct information; the only waste is a mild restatement of the read-only annotations.

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, yet the description still frames what the quote returns (billing modes, estimated costs, durations) and — crucially — explains the ambiguous case where quotedDurationSeconds is shorter than sourceDurationSeconds. Prerequisites, alternatives and failure behavior are all covered, so nothing an agent needs to call this correctly 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?

Schema coverage is 100%, so baseline is 3, but the description adds cross-call semantics the schema does not state: pass the same projectId, audioAssetId and organizationId as translation-previews_create so the quote matches the job that gets billed. That consistency requirement is genuinely new information beyond field descriptions.

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 precise verb and resource: 'Quote translating one saved audio asset', and names the operation it precedes (translation-previews_create). It also explicitly separates itself from the full-dub path (dubbing_create / generations_estimate-cost), so an agent can route without inspecting 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 explicit when-to-use ('price a translated-audio preview'), an explicit alternative for a different need ('for a full video dub, quote dubbing_create with workflow=translate-and-dub'), and an explicit do-not ('never submit the original'). The recovery path — save a shorter copy with audio-trims_create, then quote that asset — is spelled out step by step.

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