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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description discloses critical behaviors: the mailbox stops working immediately, data is destroyed only after a 14-day grace period, and the operation is staged rather than executed directly. It also names the exact response payload (actionId) and the required confirmation handoff. This is exactly the kind of behavioral context an agent needs for a destructive operation, and it is not available anywhere else.

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, zero filler. The core action is front-loaded ('Stage deletion of a mailbox'), followed by consequences, then the actionable workflow. Every sentence carries essential information: effect timeline, auth requirement, and the follow-up protocol. This is appropriately sized for a destructive tool with a confirmation flow.

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?

Since there is no output schema, the description correctly takes on the burden of explaining the return value and names it precisely (actionId), along with the exact next step (call executeConfirmedAction). It also covers the operational impact (immediate disablement, 14-day grace) and auth requirement. For a two-phase destructive operation, nothing an agent needs to invoke it safely is missing.

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 100% — both mailboxId and sessionKey are already fully documented in the input schema, including the osk_ prefix convention and the OAuth/device-flow distinction. The description adds no parameter-specific detail beyond what the schema provides, so the baseline of 3 applies. The mention of 'requires authentication' loosely reinforces the sessionKey role but adds no new semantics.

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 'Stage deletion of a mailbox' — a specific verb (stage deletion) paired with a clear resource. The 'stage' framing distinguishes it from an immediate-delete tool and from sibling mailbox tools like createMailbox, setMailboxPassword, and listMailboxes. The two-phase nature is explicit and leaves no ambiguity about what the tool accomplishes.

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 provides clear workflow context: it explains that deletion is staged, requires authentication, and mandates a follow-up call to executeConfirmedAction with the returned actionId. This tells the agent exactly what to do after invocation — present the summary and get confirmation. It doesn't explicitly contrast with alternatives or state when not to use it, but the workflow guidance is concrete enough that no usage confusion remains.

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