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

No annotations are provided, so the description carries the full burden. It discloses retry-safe behavior, the need to reuse idempotency keys, the durable per-item receipt, and the email:delete permission for permanent deletion. It does not cover error handling, partial failure semantics, or rate limits, but the information provided is substantive and goes well beyond the schema.

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 five sentences, each earning its place: purpose, return type, retry guidance, permission note, and API endpoint. No fluff, all critical information, front-loaded with the main action.

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 an 8-parameter, mutation-only tool with no output schema, the description covers purpose, batch size, retry behavior, permission, and return shape. It doesn't explicitly enumerate the allowed actions (left to the schema enum) or describe error scenarios, but it is reasonably complete for the complexity level.

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 high, but the description adds meaningful semantics beyond the property descriptions: it explains how to use the idempotency_key correctly after timeouts, connects 'up to 100 messages' to message_ids, and clarifies the permission needed for delete_permanently. This is valuable guidance not present in the schema.

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 a specific verb+resource: 'Apply a retry-safe lifecycle action to up to 100 messages.' This distinguishes it from sibling tools like mark_messages_read or delete_messages by covering multiple possible actions (move, mark_read, star, etc.) and explicitly noting the batch limit.

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 gives clear context for when to use the tool: for batch lifecycle actions with retry safety. It does not explicitly name alternatives or state when NOT to use it, but it does note a permission requirement ('Permanent deletion requires email:delete'), which is useful guidance. Minor gap: no comparison with sibling tools like mark_messages_read.

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