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

Annotations already flag destructiveHint=true, and the description builds on that by disclosing the irreversibility ('This cannot be undone'), a non-obvious side effect ('Audio you already made with that voice still plays'), and a cost signal ('Free'). This adds real behavioral context beyond the structured annotation.

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?

Front-loads the action and its reusability constraint, then ordering the caution, side-effect, and cost notes. Every sentence carries distinct information with no padding.

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 single-parameter destructive tool with no output schema, the description covers scope, irreversibility, precondition, side effects, and cost. Nothing an agent needs to call it safely is missing.

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 coverage is 100% for the single voice_id parameter, whose description already directs the agent to list_voices. The description reinforces the same source but adds no new format or syntax detail, so the baseline of 3 is appropriate.

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 ('Remove') and resource ('your own voices'), and immediately scopes it against siblings by limiting it to cloned/designed voices and excluding library voices. An agent can distinguish this from clone_voice, design_voice, or voice without opening a 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 states when the tool works ('only works on a voice you cloned or designed yourself'), when it does not ('ready-made library voices cannot be removed'), and the recommended precondition (check the name with list_voices, mine_only true). Nothing is left to inference.

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