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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false), and the description goes meaningfully beyond them with cost (1 credit per started 100 characters), latency ("Instant"), and the output artifact with its 24 h signed-link expiry — the latter being essential since there is no output schema. The only gap is that it doesn't explain failure modes (e.g. text over 5,000 characters or an invalid voice_id).

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?

One dense, front-loaded sentence plus four short clauses covering speed, price, and return format. Every element earns its place and the capability statement comes first.

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?

For a paid generation tool with no output schema, the description supplies the details an agent otherwise could not know: cost model, synchronous/immediate nature, and the signed-link return with 24 h validity. Combined with 100% schema coverage and explicit annotations, nothing material is missing for correct invocation.

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%, so text, speed, language, voice_id, and idempotency_key are all documented in the schema itself. The description restates the character cap and points at the two lookup tools for voice_id/language, but adds no syntax or format detail beyond that, so the baseline 3 applies. Notably it does not mention the idempotency_key parameter at all, despite that being the mechanism that prevents double charging.

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 gives a specific verb (turn text into), the resource (MP3 voiceover with an AI narrator voice), and the hard input ceiling (5,000 characters). No sibling in the list produces audio from text, so an agent can immediately tell this is the text-to-speech path rather than create_short or studio_generate.

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?

It names the prerequisite lookups (list_voices for voice_id, list_languages for language) which is real routing help, but it never states when to prefer this over adjacent generation tools such as studio_generate or create_short, nor any when-not condition. Usage is implied by the capability statement rather than spelled out.

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