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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: the deletion is irreversible ('No undo') and the address is permanently retired, plus the cascade to mail and attachments. It does not mention auth/permission requirements, but for a destructive mutation this is solid added value.

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, front-loaded sentences with zero filler: action, scope, confirmation requirement, and irreversibility. Every sentence 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 annotations cover the safety profile. The destructive warning, cascade scope, and confirmation requirement make it nearly complete; only the inbox_id semantics remain unaddressed.

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 coverage is 0% and there is one required inbox_id (UUID), so the description carries the burden. 'Confirm the exact address' hints at identifying the right inbox but never clarifies that inbox_id is a UUID or how to obtain it, leaving the sole parameter under-explained.

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 ('Permanently delete') and resource ('an inbox'), and immediately scopes the blast radius ('all its mail and attachments'). This distinguishes it cleanly from siblings like delete_message, delete_thread, and delete_draft.

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 requires human confirmation of the exact address and full scope before proceeding, which is strong usage guidance for a destructive op. It stops short of naming alternative tools (e.g. update_inbox, list_inboxes) for the agent to consider instead.

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