generate_sts

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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, openWorldHint=true), and the description adds substantive behavior beyond them: the call blocks until audio is ready, timeout/cancellation may leave backend synthesis running, unknown submissions are never retried, and budget is drawn from credits or characters. These are exactly the traits an agent needs before invoking a blocking paid operation.

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 action and execution mode, then workflow, then requirements, then failure semantics. Information-dense but every sentence carries operational value; slightly packed for a single paragraph but no filler.

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 does the work of describing the return (completed result with model and available voice name, plus a task_handle) and the follow-up step. Roles are clarified ('Label this as the converted result, not the source audio') and failure behavior is covered. The only gap is the unexplained quote_id and the low schema coverage around budget semantics.

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 33%: only request_id is documented in the schema. The description compensates partially by mapping budget to 'credits or characters' and describing request_id as stable, but quote_id is never explained (its provenance from estimate_sts_cost or the generation plan flow is left implicit). Adequate but with a real gap on a required parameter.

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 (Generate) and resource (STS) and immediately pins the execution mode: 'this call waits for audio and returns the completed result.' It also differentiates itself from the async pattern used by sibling tools by stating 'No extra get_generation_task polling is required.' An agent can identify this as the synchronous speech-to-speech generator without opening the 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?

Gives clear post-call routing ('call preview_audio_task with the returned task_handle'), preconditions ('Requires a quote, stable request_id and budget'), and an explicit negative ('No extra get_generation_task polling'). It lacks an explicit when-not-to-use or a named alternative (e.g., an async path), so it stops short of a 5.

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