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

With no annotations, the description carries the behavioral disclosure burden, and it discloses a great deal: 202 job id, polling via getApiJob, result field behavior, credits charged, API key requirement, and the 429 pending-jobs limit. However, it contains an internal contradiction by saying "there is no separate polling step" while later instructing to poll getApiJob until succeeded, which could mislead an agent.

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?

The description is long but dense and front-loaded with the primary purpose, then moves through workflow, constraints, limits, errors, and credits. It earns most of its length, though the contradictory polling sentence and single dense paragraph could be tightened and restructured for clarity.

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?

Given no output schema and a nested request body, the description is remarkably complete: it explains async behavior, polling, success result shape, error codes for invalid duration and quota exhaustion, credit cost, auth requirements, idempotency via request_id, and how to locate results later. This is sufficient for an agent to call and consume the tool correctly.

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?

The schema already documents all parameters with 100% coverage, so the baseline is 3. The description adds meaningful semantics beyond the schema: duration must be 0 or multiples of 10 up to 180 with 400 on out-of-range, description is required, and request_id can be used to locate the result via GET /assets/audio/results. It does not expand on augment_prompt but the schema already covers that.

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?

The description opens with a concrete verb and resource: "Produce a piece of music from a text description," and explicitly names the musical domain with examples like "epic orchestral battle theme". It also differentiates itself from sibling tools by directing songs and scores to this tool and sound effects, ambiance, and audio transforms to their respective tools.

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?

The description gives explicit when-to-use guidance: use this for songs and musical scores, use createSoundEffect for short effects, createAmbiance for looping soundscapes, and createAudioTransform for remixing audio. It also explains the async workflow, rate limit, and polling against getApiJob, leaving little ambiguity about invocation.

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