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

Annotations already declare destructiveHint=true, and the description reinforces that with 'destructive mailbox action.' It adds valuable context about ID instability: the ID changes on move/update, and it must be the latest one. It also warns against passing RFC Message-ID or stale IDs. These are beyond annotations and help avoid misuse.

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 description is a long, dense paragraph, especially for email_id, mixing prerequisites, warnings, and ID acquisition steps. It front-loads the core action but then becomes a wall of text without bullets or clear sectioning. While informative, it is not concise or well-structured for quick consumption.

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?

Despite verbosity, it covers all critical operational details: how to resolve the ID, when it becomes invalid, what to never pass, and how to handle the optional account_id with multiple accounts. With no output schema, it explains the return behavior implicitly via 'destructive action.' An agent can safely invoke it correctly after reading this.

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%, and the description essentially repeats the same text for email_id and adds a concise account_id explanation. It does not add meaning beyond the schema; it mirrors it. Since the schema already documents the parameters thoroughly, a baseline of 3 is appropriate; no extra semantic value is provided by the description.

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 states a clear verb and resource: 'Trash one exact email.' It also flags it as a 'destructive mailbox action,' which sets expectations. It does not explicitly contrast with sibling tools like email_move_or_label, but the purpose is unambiguous and not a tautology.

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?

No guidance on when to use this tool versus alternatives. It does not mention that email_move_or_label could be used for moving to trash, or that this is a permanent action, nor does it specify prerequisites beyond resolving the ID. The only context is 'destructive mailbox action,' which implies but does not state selection criteria.

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