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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description's added value is the ownership constraint ('belonging to the caller'), which hints at a failure mode when the voice is not owned, but it says nothing about irreversibility, impact on existing audio using that voice, or error behavior.

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?

One short sentence with the action and scope front-loaded and no filler. The trailing clause 'when explicitly requested' is a bit soft for a destructive operation but still carries usage intent rather than being wasted words.

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?

An output schema exists, so return values need no explanation, and the tool surface is small (one required string). However, for an irreversible destructive operation the description stops short of covering the ownership precondition, confirmation expectation, and consequence of deletion, which are the details an agent most needs here.

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 single parameter voice_id has 0% schema description coverage, so the description carries full burden but never mentions the parameter at all. It does not say where a voice_id comes from (e.g., list_voices) or what format it takes, leaving the only required argument undocumented in both structured and prose form.

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 and resource ('Delete a saved cloned voice') and scopes it to the caller's own voices. It is clearly distinct from the other destructive siblings (delete_style_guide, delete_subtitle, delete_translation_memory_entry) which operate on different resources, though it does not explicitly name them.

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?

'When explicitly requested' is a light usage signal implying this should not be called speculatively, and 'belonging to the caller' implies an ownership precondition. There is no explicit when-not guidance, no mention of alternatives such as list_voices to find the right voice_id, and no stated prerequisite for confirming intent with the user.

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