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

Annotations only declare the generic safety profile (destructive, openWorld, non-idempotent); the description adds the operationally critical context: the send is queued and not confirmation of provider completion, attachments are dropped, the body is quoted, and retries must reuse the same operationId. This is exactly the extra behavioral depth the annotations do not supply.

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?

Five short sentences, each carrying a distinct constraint, with the core action and the two sharpest warnings front-loaded. No filler or repetition.

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?

Covers the async/queued lifecycle well, which is the highest-risk aspect, but leaves several required inputs (accountId, messageId, senderIdentityId) and the recipient fields unexplained, and 'the returned operationId' is ambiguous when operationId is also a required input the caller supplies. Adequate for safe invocation, incomplete for the schema's complexity.

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 13% (essentially just operationId), so the description must compensate and largely does not: to/cc/bcc, accountId, messageId, and senderIdentityId are undocumented in both places. The only parameter-adjacent information is that textBody is an 'optional note' and the retry semantics for operationId, which is thin for an 8-parameter tool.

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+resource (forward a message) and adds distinguishing detail: the original body is quoted and attachments are not forwarded, which separates it from reply_to_email and send_email. It stops short of explicitly naming the alternative sibling, so it is clear but not sibling-routing.

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 strong downstream workflow guidance (poll get_mail_action with the returned operationId; never retry an uncertain send with a new operationId) but never says when to choose this over reply_to_email, send_email, or create_draft. Usage is implied by the action name rather than contrasted with alternatives.

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