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

Beyond the destructiveHint annotation, the description discloses permanence, non-reversibility, no id reuse, storage freeing, account-wide usage semantics, refusal behavior naming affected Riddles, and unresolved references. This is rich behavioral context that materially helps an agent decide and call safely.

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?

The description is long but every sentence carries essential safety, usage, or workflow information. It front-loads the core action and cleanup purpose, then layers conditions and consequences without redundancy.

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 destructive tool with one parameter and no output schema, the description is fully complete: it covers purpose, prerequisites, failure behavior, irreversibility, return shape, and user consent. There are no meaningful gaps.

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?

The input schema already documents mediaId with a clear description, and schema description coverage is 100%. The tool description does not add much parameter-specific detail, but none is needed since the schema covers the single parameter well.

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 uses a specific verb and resource: 'Deletes a file from the media library permanently.' It also clarifies the intended cleanup use case and distinguishes itself from Riddle-related operations by explaining that the file must be unused and that Riddle references block 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?

It explicitly says when to use the tool (cleanup after a bad upload or unneeded file), when notto use it (file still used by any Riddle), and gives the exact alternative workflow (riddle_builder_update, then riddle_publish) before deletion. It even advises asking the user first because deletion is permanent.

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