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

Annotations only say the operation is a non-read, non-idempotent, non-destructive write. The description adds the material context the annotations lack: the password is encrypted for the executor, never returned, guest access is excluded, members get read-only access while owners/admins/org keys may manage, and the private service credential stays server-side.

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?

Purpose is front-loaded, but the body is a stack of terse fragments and the never-returned point is stated twice ("is never returned" and "Mailbox passwords and message content are never returned"). The line about the private service credential is generic security boilerplate that does not directly serve this call.

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 parameterized write with no output schema and thin annotations, the description covers the key agent questions: secrecy of the value, who is authorized, and that no secret is echoed back. It omits what happens to the prior password and how idempotency_key behaves, which keeps it from a 5.

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 100%, so all four parameters (password length/charset rules, resource_id, organization_id, idempotency_key) are already documented in the schema. The description adds no per-parameter meaning beyond that, so the baseline 3 applies.

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?

"Set the mailbox password" is a specific verb+resource that clearly separates this tool from sibling mailbox_create, mailbox_update, mailbox_suspend and mailbox_resume. It does not explicitly name a sibling it differs from, so it stops short of a 5.

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?

Usage is implied by the purpose (rotating/setting a mailbox password) and the permission sentence ("Owners, admins and organization keys can manage email") tells the agent who may call it. There is no statement of when to use this instead of mailbox_update, nor any prerequisite/exclusion guidance.

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