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

Adds substantial context beyond the annotations: delete is permanent but retains the name in existing audio, turn_off removes the voice from all pickers while keeping it on the account, only the owner can modify, the operation is free, and the agent should confirm verbally before deleting. This directly complements destructiveHint=true with actionable safety guidance.

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-loaded with the tool's identity, then action semantics, then prerequisite (list_voices), constraint (owner-only), and safety. It is dense and single-block, which makes scanning the delete warning slower, but nearly every clause carries information.

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, no-output-schema tool, it covers what each action does, how to identify the target voice, how to check current state, permission constraints, and irreversibility. Nothing needed to invoke it correctly 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%, and the description still adds meaning: voice may be spoken as the person's name or its id, and each action string is explained behaviorally rather than just enumerated. Slightly above baseline.

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+resource and enumerates exactly what each action does, plus scopes it to the owner's own voices (Seed Audio clips and trained voices). It does not address the overlapping sibling delete_voice, leaving ambiguity about which tool to use for deletion.

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?

Clearly says when each action applies (turn_off vs delete vs share vs unshare) and routes the agent to list_voices with mine_only true to see current state. Missing: guidance on when to prefer this over the standalone delete_voice/clone_voice siblings.

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