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

Adds genuinely non-obvious behavior beyond annotations: the call is queued and its return is not provider confirmation, plus the idempotency-key reuse rule on retry. Annotations supply destructive/openWorld/non-idempotent, so the remaining gap is what archiving actually does (folder destination, reversibility) for a destructiveHint 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?

Four short, front-loaded sentences with no filler; the async caveat comes immediately after the purpose. Minor blemish: 'Never retry an uncertain send' uses 'send', a copy-paste artifact for an archive tool, which slightly muddies the retry rule.

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?

With no output schema, the description still tells the agent what comes back (an operationId) and how to resolve it, which is the critical missing piece for an async tool. It omits what the archive operation does to the mailbox and any permission requirements.

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 coverage is only 33% — only operationId is documented in the schema — and the description reinforces the operationId retry semantics but says nothing about accountId or messageId. It partially compensates for the coverage gap but leaves two of three parameters unexplained.

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 and resource ('Archive a message from its current folder'), which is more precise than a generic move and distinguishes it from delete/move siblings by naming the archival scoping. It never explicitly contrasts itself with move_email, which could also relocate a message, so it stops short of full sibling differentiation.

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?

Gives concrete follow-up guidance: poll get_mail_action with the returned operationId, and never retry with a new operationId. However, it offers no guidance on when to choose archive_email over move_email or delete, and no prerequisite/auth context.

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