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

No annotations exist, so the description carries the full behavioral burden. It discloses the returned catalog fields and the disambiguation rule versus delivery instructions, but says nothing about pagination (the limit parameter implies paging), auth/workspace scoping, or response shape.

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?

Three short sentences, front-loaded with the core action, then the usage rule and the caveat. Every sentence contributes and nothing is redundant.

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?

No output schema and no annotations for a 6-parameter tool, so the description must cover more ground. It conveys returned fields and selection intent adequately, but omits pagination behavior, the required workspaceId, and filtering semantics.

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 50%: name, language, and workspaceId are documented; gender, limit, and provider are not. The description's mention of 'names, gender, languages' loosely maps to the filter fields but adds no format or default/syntax detail 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?

States a specific verb (List) and resource (Cartesia voice IDs) and enumerates the returned attributes (names, gender, languages, accents). An agent can distinguish this from mutation siblings like change_audio_track_voice or generate_audio 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?

Explicitly directs the agent to resolve narration preferences with this catalog before choosing voiceId, and warns that 'delivery instructions alone do not select a Cartesia voice.' That is clear when-to-use context, though it never names a specific alternative tool to compare against.

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