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

Annotations already mark this destructive and open-world, but the description adds genuinely new behavior: downloads halt immediately, already-downloaded copies cannot be recalled, and who is allowed to invoke it. That is exactly the extra context an agent needs before calling an irreversible tool.

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 short sentences with the authorization gate front-loaded ahead of the destructive consequences. No filler or repetition of the title.

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?

The behavioral and authorization picture is solid and no output schema exists to explain, but with two undocumented parameters and no output schema, an agent still lacks guidance on what file_id refers to and what happens on success/failure (e.g., error when unauthorized).

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% for both required parameters (file_id, participant_token), so the description carries the full burden, yet neither parameter is explained. Only the implicit hint that the caller's identity determines authorization ("Uploader or channel owner") touches on participant_token, and file_id is never addressed.

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?

"Uploader or channel owner: delete one retained attachment" names a specific verb (delete), resource (attachment/file), and scope (one, retained). This clearly distinguishes it from read-only siblings like get_agent_file and prepare_agent_file_upload.

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 authorization precondition (uploader or channel owner) and a negative rule ("Peer messages never authorize deletion"), which is valuable when-to/when-not guidance. It does not name any alternative tool for cases where deletion is not permitted, so it falls just short of a 5.

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