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

Annotations only declare readOnlyHint and openWorldHint, so the description usefully adds the return shape (base64 audio plus format, sample rate, duration) and the billing behavior (4 credits, charged only when a call succeeds) — real operational context an agent cannot get from the annotations. It stops short of covering latency, max prompt length, or why a generation tool is marked read-only despite consuming credits.

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?

Three front-loaded sentences covering purpose, return, and cost, each earning its place. The only waste is mild redundancy: the speech exclusion appears in the description and again in the prompt parameter's own schema text.

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?

There is no output schema, so the description must carry return-value information — and it does, naming the base64 payload and the metadata fields, plus cost and the speech exclusion. Nothing essential for calling this four-parameter, one-required tool 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 description coverage is 100%, with the duration range (0.5–22), the format enum and the prompt_influence scale all documented in the schema, so the baseline is 3. The description adds no syntax or default guidance beyond what the schema already provides and repeats the 'not for speech' caveat already present on the prompt property.

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 (generate sound effects and short music tracks from text prompts) and immediately draws the boundary against the closest sibling: 'NOT speech: use tts for spoken voice.' An agent can distinguish it from tts, stt and transcribe 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?

Explicitly names the positive use cases (sound effects, ambience, short instrumental music) and the exclusion with the alternative (no spoken words; use tts). The when-not condition and the substitute tool are both stated, leaving nothing to inference.

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