get_candidate_audio

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

Annotations already mark the tool as readOnly and idempotent. The description adds valuable behavioral context: it loads previews into the picker and explicitly denies generation, selection, or installation behavior. This goes beyond the annotations and helps set expectations about side effects.

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 two short sentences with no filler. The primary action is front-loaded, and the exclusion clause is a distinct second sentence. Every word contributes meaning.

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 one optional parameter and no output schema, the description leaves important gaps: what generation_id means, what happens if it is omitted, and what the return/result of the load looks like. Annotations cover safety but not invocation semantics, so the description is not complete enough for confident correct use.

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?

The schema has one parameter, generation_id, with no description coverage. The tool description does not mention this parameter at all, leaving the agent to guess what generation_id refers to, why it is optional, or how it affects the operation. With 0% schema coverage, the description needed to compensate and did not.

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 uses a specific verb ('Load') and a clear resource ('existing audio previews') with a destination ('into the picker'). It also explicitly states what the tool does not do ('Does not generate, select or install audio'), which clearly differentiates it from sibling tools like generate_sound_candidates, select_sound_candidate, and install_sound_candidate.

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 gives clear context for when to use the tool: when loading existing audio previews into the picker. It also states exclusions ('Does not generate, select or install audio') which signals what not to use it for, but it does not explicitly name alternative tools or provide conditional guidance, so it falls just short of a 5.

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