trash_mail

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, covering the safety profile. The description adds useful behavioral context: the never-issues-EXPUNGE guarantee and the confirmation requirement. However, it doesn't disclose what happens to the mail in the trash (recovery options, retention), which limits the additional value beyond annotations.

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 crisp sentences, zero filler. Every word earns its place — action, scope, and a critical safety guarantee are all front-loaded in minimal space.

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?

The tool has 4 required params and an output schema, and is a destructive operation with a confirm safeguard. The description covers the action and the confirm gate, but given the destructive nature, it could disclose more about side effects (HAS output schema helps, but the safety-critical confirm mechanism deserves more explicit callout about what happens without the confirm value).

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 must compensate for parameter meaning. It names confirm='TRASH' as a required confirmation value and references folder/trash_folder implicitly, but doesn't explain what each of the 4 parameters means in detail (e.g., what 'folder' is versus 'trash_folder'). Partial compensation for the coverage gap.

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 clearly states the action ('Move one UID to a named trash folder') with a specific verb, resource, and destination. It distinguishes somewhat from the sibling 'move_mail' tool through the trash-specific naming and confirm requirement, though it doesn't explicitly differentiate the two move operations.

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 usage context (moving a single mail to trash, requiring a confirm='TRASH' param), but provides no explicit guidance on when to choose this over move_mail or other alternatives. The confirm requirement provides some usage guardrail but no comprehensive when/when-not guidance.

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