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

Annotations already declare a safe read-only, closed-world operation. The description adds value beyond that by disclosing the default scope value, the fact that a clone limit is returned, and that returned ids feed generate_speech — behavioral context not present in the structured fields.

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 compact clauses, each earning its place: scope semantics, default value, and downstream usage. Scoping information is front-loaded with no filler.

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 low-complexity, zero-required-param list tool with read-only annotations and no output schema, the description covers the only real decision (which scope) plus a downstream pointer. Minor gap is no mention of ordering, pagination, or returned fields, but none is required 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?

Schema description coverage is 0% and the single enum parameter has no inline documentation, so the description must carry the load. It does: both 'mine' and 'premade' are defined and the default is stated, fully compensating for the coverage gap, though it adds no output-shape detail.

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 makes clear this enumerates voices and what each scope bucket contains ('your cloned and saved voices, plus your clone limit' vs 'preset voices anyone can use'). It implicitly separates this from the single-voice sibling get_voice by pointing to the downstream generate_speech use of an id, though it never names get_voice directly.

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?

States the default ('mine') and what each scope yields, so an agent knows which value to pass without extra inference, and it signals the follow-up action (passing an id to generate_speech). It stops short of explicitly contrasting with get_voice or delete_voice/create_voice_clone.

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