Delete emails

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

destructiveHint=true already tells the agent this is a destructive operation, and the description's omitting-messageId clause usefully adds that the bulk case wipes an entire address rather than one message. However it never states irreversibility, whether deletion can be undone, or any auth/ownership requirement — gaps that matter for a destructive tool with a low annotation bar.

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?

Two tight sentences, with the branching behavior front-loaded and the motivating use case last. No filler or redundancy.

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 two-parameter tool with no output schema, the description covers both the single and bulk modes and the intended cleanup scenario. The remaining gap is that a destructive operation is not flagged as irreversible and messageId's provenance is unstated, but the destructiveHint annotation partially compensates.

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 0%, so the description carries the burden, and it does convey the key semantics: messageId present means one message, absent means all mail at address. It does not explain the format/origin of messageId (e.g. obtained from list_emails or read_email) nor the address format, so coverage is good but not complete.

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 (delete) and resource (email/emails), and explicitly disambiguates its two operating modes: single message via messageId, or the whole mailbox at an address when messageId is omitted. Among siblings (list_emails, read_email, create_test_address) only this tool deletes, so its role is unmistakable.

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?

"Clean up after a test" gives one intended context and hints at a paired workflow with wait_for_email/read_email, but there is no guidance on when not to use it, no warning about permanent loss, and no mention of constraints (e.g. only owned test addresses). The usage context is implied rather than spelled out.

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