walkthrough_voice_selection

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

No annotations are provided, so the description carries the behavioral burden. It discloses that passing `voice` switches to a specific voice and plays a sample, `list: true` avoids playing audio, `audition: true` plays voices back-to-back, and that voice selection persists across sessions. It does not mention side effects like requiring an active walkthrough or network usage, but covers the main state-changing and persistence behaviors well.

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?

The description is appropriately sized and front-loaded with the core actions, then the usage triggers and exclusions, then parameter guidance. Every sentence carries useful signal without redundancy or irrelevant detail. The structure flows from high-level purpose to specific parameter behavior.

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 tool with 5 parameters and no output schema, the description covers the key decision points: what each parameter does, when to use the tool, and a critical exclusion (toggle vs. settings). The only minor gap is not describing the shape of the response (e.g., what the list output contains), but the parameter list and examples make it largely inferable.

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 the schema already documents each parameter. The description adds value by linking parameters to high-level intents (e.g., 'Pass `list: true` to list voices without playing audio') and by giving examples of locale prefixes and voice names. It reinforces and clarifies, though it does not introduce entirely new parameter meaning beyond the schema.

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 clearly states the specific operations: change the narration voice, preview it, list available voices, and audition voices back-to-back. It names the resource (narration voice) and distinct actions. It also differentiates from the settings tool by explicitly saying 'Do NOT use to toggle voice on/off'.

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?

The description provides explicit usage conditions: use when the user asks to change the voice, try a different voice, hear voice options, compare voices, or asks 'what voices are available'. It also states a clear exclusion (use settings tool for toggling) and explains when to pass `voice`, `list: true`, `audition: true`, `locale`, and `gender`. This is outstanding guidance for an agent.

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