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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real value on top: the folder restriction, the refusal behavior, the absence of undo, and the two-phase confirmation protocol naming status='confirmation_required', action_id and plan_token with confirm_action as the follow-up. That is substantial behavioral disclosure beyond the annotations. The score is held below 5 only because the description does not describe what the intermediate confirmation response contains beyond the status and IDs, nor what happens to the plan_token's validity.

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 scope, then preconditions, then the confirmation protocol; nearly every sentence carries decision-relevant information. Minor redundancy in 'from anywhere else it is refused, whatever the reason given' and the 'To really delete ...' restatement keeps it from a 5.

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, confirmation-gated tool with no output schema, the description covers the safety model, the refusal conditions, and the follow-up call an agent must make. The one real gap is the input parameter itself, whose format and 50-item ceiling are left entirely to the schema.

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?

There is a single required parameter, message_ids, and the schema description coverage is 0% – yet the description never mentions it, its accepted ID formats (integer or string), or the 1–50 item limit. The description therefore adds nothing to compensate for a schema that only conveys structure, leaving the agent to infer what identifiers are acceptable.

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?

Names a specific verb ('Erase ... for good') and resource ('messages from the mail server'), and immediately distinguishes itself from softer deletion siblings by stating the permanence and the Trash/Spam-only constraint.

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?

Explicitly states when the tool is allowed (Trash or Spam folder) and when it is refused (anywhere else, no exceptions), plus the exact prerequisite workflow: 'mail_move it to trash first, then this'. It routes the agent to a named sibling for the inbox case, which is precisely the guidance needed.

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