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

Annotations already mark the tool destructive and non-idempotent, but the description adds substantial behavioral context: MEDIA_TRASH determines whether the item moves to trash with an undo token or is permanently removed, force: true bypasses refusal and has no undo, and Royally waits for human approval before anything changes. This materially exceeds what the annotations provide.

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 front-loaded with the core action, then proceeds to the trash/force/approval conditions without filler. The parenthetical site context is brief and the Royally approval note is directly relevant to invocation timing.

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 no output schema, the description is complete enough to invoke correctly: it covers the required id, the force condition, trash behavior and undo token, permanent deletion with no undo, and the human-approval delay. No critical decision point is left unexplained.

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 schema already documents force and site_id, and the description adds conditional meaning for force: it is refused unless force: true when trash is off or the item is already trashed, and force: true always permanently deletes. The id parameter is left implicit, but it is a required integer and schema coverage is already 67%.

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 first sentence states a specific verb and resource: 'Delete a media item.' The resource 'media' paired with the delete action clearly separates it from sibling get/update/upload media tools and from post/comment deletion tools, so an agent can identify the operation without opening the 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?

The description explains exactly when force is required: when media trash is off or the item is already trashed, deletion is refused unless force: true, and force: true always deletes permanently. It does not name an alternative tool or tell the agent when to use a different sibling instead, so explicit alternatives are absent.

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