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

Annotations already cover readOnly/idempotent/destructive hints, so the description earns full credit for additional behavioral context: 'Locale marks a voice's primary language rather than a limit', 'Private customer voice clones are never listed', and 'Genpio resells no third-party TTS'. These disclosures tell an agent important things it could not infer from the annotations — that all listed voices have certain licensing characteristics and that the list intentionally excludes certain content.

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 purpose is front-loaded in the first sentence, and the Locale caveat is valuable. However, the second half contains a very long passage about the model architecture (Qwen3-0.6B, OmniVoice Apache-2.0), training corpus IDs (SLR37, SLR41-44, etc.), and redelaration that Genpio uses its own GPUs — this repeats 'Genpio's own GPUs' twice and gives more detail than an agent needs to call the tool. A shorter 'trained in-house, open license, see model card' would be sufficient.

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?

Though there is no output schema, the description explicitly names the return fields and the `matched` count, explains the semantics of Locale, and discloses exclusion rules (no clones, no third-party TTS). With the full schema documentation and the readOnly/idempotent annotations, there is genuinely nothing missing for an agent to decide whether and how to call this tool.

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%, and the schema already explains the limit parameter's behavior (returning a `matched` count rather than counting the array) and the language parameter's regional-variant matching. The description does not add parameter-level details beyond restating that language and gender filter; the schema does the heavy lifting, so the baseline of 3 applies.

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 opening sentence names a specific verb and resource: 'Search Genpio's public voice catalogue' and the filters (language, gender) that define the tool's scope. It also enumerates the exact return fields (DisplayName, ShortName, Gender, Locale, LocaleName, total) so an agent knows exactly what this tool produces. The focus on voices clearly differentiates it from siblings like list_avatars, list_open_roles, and service_status.

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 establishes clear context: use this tool when a voice needs to be searched or filtered from the public catalogue. The explicit mention that only public voices are returned, and the wording 'Search Genpio's public voice catalogue', imply when it should not be used (e.g., for avatars/roles/status). It does not explicitly name alternatives or state when-not conditions, but sibling tool names make the decision boundary obvious.

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