Create catch-all

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

Beyond the annotations, the description discloses important behavior: a confirmation email is sent, the catch-all is not active until confirmed, and a domain can have only one catch-all. These are non-obvious side effects and constraints an agent must know before calling 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 earning its place: what the catch-all does, the confirmation requirement, and the one-per-domain limit. No redundant or speculative content.

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 simple one-parameter tool with no output schema, the description is complete: it explains the mechanism, activation delay, confirmation step, and uniqueness constraint. An agent has enough information to decide when and how to invoke it.

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 input schema already fully describes the single parameter as 'Mailbox resource ID', so the schema carries the semantic load. The description adds minimal parameter-specific value beyond naming 'given mailbox', which is acceptable given 100% schema coverage.

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 uses a specific verb ('Create') and resource ('catch-all'), and clearly explains what the catch-all does: routes all messages to unknown domain addresses to a given mailbox. This distinguishes it from related sibling tools like mail_createAliasV1 and mail_createForwarderV1.

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 implies when to use it: when you want all unknown-address mail to route to one mailbox. However, it does not explicitly mention alternatives or conditions for preferring another tool, such as mail_createForwarderV1 or mail_createAliasV1.

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