select_sound_candidate

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

Annotations already communicate idempotency and non-destructiveness. The description adds a useful behavioral clarification—recording a selection does not install a file—which helps disambiguate from install_sound_candidate. However, it does not describe side effects, whether the selection is persisted, or what happens on repeated calls, though idempotentHint covers some of this. No contradiction with annotations.

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?

Two short sentences with no fluff. The main action is front-loaded, and the clarifying 'does not install a file' earns its place by preventing a common confusion. Every word contributes.

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 2-parameter tool with no output schema, the description is minimal but leaves critical workflow context missing: where generation_id comes from, how it relates to the user's 1-4 choice, and what the agent should expect after calling this. The sibling tool list hints at the workflow, but the description itself does not provide enough for confident invocation.

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 0%, so the description must compensate. It explains that the variant parameter maps to a 1, 2, 3, or 4 user reply, which is helpful. However, it never explains generation_id—its origin, how to obtain it, or its relationship to the candidates being selected. This is a notable gap given the schema provides no semantic help.

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 ('Record') and identifies the exact resource: the user's explicit 1, 2, 3, or 4 reply. It also distinguishes itself from installing by adding 'This does not install a file,' which differentiates it from the install_sound_candidate sibling. It does not explicitly name all siblings, but the core purpose is unambiguous.

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 implies this tool is used when the user provides a 1-4 selection and explicitly clarifies that it is not an install action. However, it does not state when to use this versus generate_sound_candidates or get_sound_candidates, nor does it describe the expected workflow order. Usage context is implied rather than explicit.

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