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

Beyond the annotations, it discloses rate limiting, that the call may hit a managed provider or validate BYOK, that preview-rate and exact voice-availability state get written, that the preview is neither read-only nor free, and that audio is bounded in-memory WAV. This is exactly the extra context the annotations cannot carry.

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?

Four dense sentences, front-loaded with the core action and the rate/side-effect warning, with no filler. It is packed tightly enough that the voice-type distinction and the side-effect disclosure have to share a sentence, but nothing is wasted.

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 11-parameter, nested-object tool with no output schema, the description still covers return format, side effects, and the branching voice behavior. The remaining gap is parameter-level guidance for the five undocumented required fields.

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?

With only 55% schema description coverage, the description still never explains model, provider, voice_id, language, or project_id, and its 200-character note merely repeats the schema's maxLength. The TTS-vs-conversation-engine rule does add real meaning about how text behaves, which lifts it above a pure schema restatement.

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 names a specific verb and resource ('Render one bounded, rate-limited voice preview') and immediately splits behavior by voice type (text-to-speech vs conversation-engine), so an agent knows exactly what the tool 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?

It gives strong conditional guidance inside the tool (text is honored for TTS voices, refused for conversation-engine voices, ambience requires explicit text for TTS), but it never says when to choose this over an alternative such as get_agent_voice_stack or preview_simulation_run.

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