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

Annotations only declare it is a non-read-only, non-idempotent, non-destructive write. The description adds substantial context beyond that: trial mailboxes share 1 GB and cannot send, no guest access, the read/manage role split, the service credential staying server-side, and that passwords and message content are never returned. That is exactly the kind of disclosure annotations cannot carry.

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?

The purpose is front-loaded in the first clause and every following sentence carries distinct information (trial limits, access model, permissions, secret handling). It is longer than typical but not padded; the telegraphic sentence fragments slightly hurt readability rather than length.

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 five-parameter mutation with no output schema and minimal annotations, the description covers scope, quota behavior, authorization and data-handling expectations. It stops short of describing what is returned on success or how the required idempotency_key is honored, which matters given idempotentHint=false.

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% (all five parameters documented, including local_part, domain_id and idempotency_key), so the schema already does the parameter work and the baseline is 3. The description adds no per-parameter semantics such as local_part formatting rules or what the allowance actually constrains.

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 ("Create a mailbox") and scopes it with "within the current allowance", which separates it from the update/suspend/resume/password siblings on the same resource. It does not explicitly name a sibling or state when creating a mailbox is preferred over an alias, but the resource noun is unambiguous.

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?

"Within the current allowance" implies a quota precondition, and the permission sentence ("Members can read. Owners, admins and organization keys can manage email") implies who may call it, but neither is framed as an explicit when-to-use rule. No alternatives or exclusions are named, so the agent must infer selection from the resource name alone.

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