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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description adds non-redundant context: deletion is permanent, attachments go with it, there is no undo, and human confirmation is required. It stops short of noting permission requirements or folder scope.

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?

Two sentences, zero filler, with the irreversible consequence and confirmation requirement front-loaded. Every clause earns its place.

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?

An output schema exists, so return values need no explanation, and the one required parameter is simple. The description covers permanence, attachments, and confirmation, but omits surrounding context an agent might want, such as required permissions or whether the message must be in a specific folder.

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% and there is one parameter (message_id), whose UUID format is only conveyed by the schema's format/pattern keywords, not the description. 'Confirm the exact message' hints that the identifier must be precise but adds no format or source guidance, so the schema carries the load.

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 ('Permanently delete a received email') and scopes it to received mail, which separates it from the delete_sent_message and delete_draft siblings. It does not name those siblings explicitly, so it falls short of the top score, but an agent can place it correctly.

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 a clear precondition for use ('Confirm the exact message with the human; no undo'), which is actionable guidance. It does not, however, point to an alternative tool (e.g., delete_thread for an entire conversation) or state when-not-to-use it.

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