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

With no annotations, the description carries the full burden and does well: it discloses immediate mailbox stoppage, data destruction after 14 days, authentication need, and the actionId-based confirmation flow. It does not mention whether staged deletion can be cancelled or idempotency, but the destructive impact and sequencing are clearly communicated.

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 sentences front-load the core purpose, then cover effects, auth, parameter source, return value, and the next action. Every sentence adds necessary information with no filler or 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, two-phase operation with no output schema, the description is remarkably complete: it explains the required parameter, the immediate and delayed consequences, the auth requirement, the returned actionId, and the exact follow-up call to executeConfirmedAction.

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 leaves mailboxId undocumented, but the description compensates by noting it is required and sourced from listMailboxes. sessionKey already has a thorough schema description, so the 50% coverage gap is meaningfully filled.

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 opens with a specific verb-resource pair, 'Stage deletion of a mailbox', which clearly distinguishes this from immediate permanent deletion and from sibling delete* tools. It also explains the staged nature by stating the mailbox stops working immediately but data is destroyed only after a 14-day grace period.

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 the required mailboxId comes from listMailboxes, requires authentication, and instructs to call executeConfirmedAction with the returned actionId if the user approves. This provides strong usage context and a clear follow-up, though it does not explicitly list when not to use it or mention any alternative deletion pathway.

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