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

Annotations already flag destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description adds real context beyond them: deletion is irreversible (no trash), the first call is a non-mutating preview, and only the caller's own takes are affected. This is exactly the extra context an agent needs before a destructive operation.

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 destructive fact, then the call protocol, then limits. Every clause carries information, though the trailing staccato fragments ("Up to 50 at a time. Only your own takes. Free.") read as abrupt rather than crafted.

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?

With only two parameters and no output schema, the description covers what an agent needs: what the dry-run response conveys ("lists exactly what would be removed"), the mutation semantics, the batch limit, and the ownership constraint. Nothing material is left dangling.

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%, so the baseline is 3, but the description adds meaning the schema lacks: confirm's two-phase semantics are spelled out in prose, and "Up to 50 at a time" bounds the size of generation_ids. Only the provenance of the ids (from list_my_audio) is left to the schema.

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 ("Remove your own audio takes") plus scope qualifiers (speech, dialogue, music, sound effects) and a permanent consequence ("no trash for audio"). An agent can distinguish it from delete_my_videos, delete_my_asset, and delete_voice without inspecting schemas.

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?

Gives an explicit two-call protocol: call without confirm first to preview, then call again with confirm true once the person agrees. Also states exclusions ("Only your own takes") and the batch ceiling ("Up to 50 at a time"), leaving nothing to inference about when and how to invoke it.

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