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

Annotations only declare the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false); the description adds substantial context on top: 3 credits per call, credits held on acceptance and refunded on failure/cancellation, HTTP 400 for out-of-range duration, and the async job contract returning `{id, status}` polled via getApiJob. The only gap is a slightly awkward fit between the async job contract and the 'single audio result' phrasing, which the agent must reconcile (job result vs. immediate return).

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 examples, then routing, then constraints, then the async contract – a sensible ordering. It is dense but nearly every sentence carries decision-relevant information; minor waste in restating that the description field is required, which the schema already declares.

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 takes on the burden of explaining returns and does so: an intermediate `{id, status}` job object to poll via getApiJob, and a final single audio result whose .mp3/.wav extension indicates format. Combined with credit and error behavior, an agent has everything needed to call and follow up 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?

Schema coverage is 100%, so baseline is 3; the description earns an extra point by restating the critical constraints in prose (duration must be 0 or multiples of 10 up to 180, out-of-range gives HTTP 400; loop=true for seamless looping) and by explaining request_id's dual role as a dedup key and a listGenerations filter, which goes beyond the schema's local wording.

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 and resource ("Produce a piece of music from a text description") with two concrete example prompts, so the agent knows exactly what it generates. It also explicitly names the sibling tools it is not (createSoundEffect, createAmbiance, createAudioTransform), making it distinguishable without opening any 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 an explicit routing rule: songs and musical scores here, short effects to createSoundEffect, looping backgrounds to createAmbiance, remixing to createAudioTransform. It also notes the optional request_id path for later retrieval via listGenerations, so the full workflow is implied.

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