create_mailbox

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that the tool returns real IMAP/SMTP AUTH credentials, that a strong password is auto-generated if omitted, and that this generated password is only shown once and cannot be recovered later, only reset. This is precisely the kind of behavior an agent needs to know before invoking the tool.

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, each with a distinct job: scope and prerequisite, output and use case, and critical password behavior. No filler, no repetition, and the most important operational details are front-loaded.

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?

Given the absence of an output schema and annotations, the description covers everything needed to call the tool correctly: what it does, the prerequisite domain registration, the required and optional parameters, the return value, and the crucial one-time-password behavior. There are no obvious operational gaps for this level of complexity.

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 already describes all three parameters with useful examples, so the baseline is 3. The description adds meaningful context beyond the schema by emphasizing that the domain must already be registered and by explaining the password auto-generation and one-time return behavior. That lifts it above the baseline.

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 ('Create a mailbox') and gives a concrete example (hello@example.com). It explicitly ties the operation to create_domain, which distinguishes it from sibling tools like list_mailboxes, delete_mailbox, and reset_mailbox_password.

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 clearly states the prerequisite: the domain must already be registered via create_domain. It also gives a practical use case (adding to mail clients) and notes that a lost password is only resettable, implicitly pointing to reset_mailbox_password. However, it does not explicitly name alternative tools or state when not to use it, so it falls just short of a 5.

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