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

Annotations declare a mutating, credit-consuming, non-idempotent operation, and the description substantiates that with real behavioral detail: exact output artifacts (MP3 audioUrl, r2Key reusable as a source in other tools, word list), the 1-credit-per-500-character cost, the 5000-character ceiling, the absence of speed control, and how inline tags like [laughs] are performed but excluded from timings. This is context the annotations cannot express.

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?

Dense but front-loaded, using SYNC/voiceId/Models labels to make it scannable, with the highest-value facts (output artifacts and cost) leading. A few clauses are tightly packed but none is 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?

For an 8-parameter paid generation tool, the description covers the deliverables, the cost model, the limits, model selection, and tag behavior. The remaining gap is the numeric style/stability/seed parameters, which neither the schema nor the description explains, but an output schema exists so return-value detail is not required.

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 only 25% across 8 parameters, so the description must compensate, and it does explain voiceId sources, modelId options, and text length. However it says nothing about seed, style, stability, similarityBoost, or languageCode, leaving half the tuning surface undocumented in both places.

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 (text-to-speech generation) and immediately narrows scope by highlighting the word-timestamp output that distinguishes it from plain audio generators like studio_generate_audio or voice_enhance. An agent can tell what it produces 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 routing for voiceId (list_voices, or scope 'premade') and states cost and character limits up front, so the agent knows the preconditions before calling. It does not, however, contrast itself against the many overlapping audio siblings (studio_generate_audio, voice_enhance, dub_video), so the when-not guidance is incomplete.

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