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

The description discloses important behavior beyond annotations: it never sends, the server includes original headers and plain text, the draft requires user review and approval via approvalUrl, and requestKey must only be reused for identical retries. This aligns with the idempotentHint annotation and adds substantial context.

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 dense but every sentence earns its place. The most important facts—what the tool does and that it never sends—are front-loaded, followed by constraints, user approval requirements, and retry semantics in a logical order.

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?

Given seven parameters, no output schema, and minimal annotations, the description covers the response essentials (complete draft, warnings, approvalUrl), exclusion cases, user-approval behavior, and retry semantics. There is no critical information an agent needs to select or invoke this tool correctly.

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?

With schema description coverage at 0%, the description carries the burden and does add real semantics: text is optional, omitAttachments has a specific agreement condition, recipients must come from the user request, and requestKey is for identical retries. Remaining parameters like mailboxId, messageId, and cc are left to their self-explanatory names, which is a minor 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 identifies the action (prepare), the resource (an existing email), and the modality (text-only forward). The explicit 'This NEVER sends' plus 'forward of an existing email' distinguishes it from sibling draft tools like prepare_draft and revise_draft.

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?

It gives explicit when-to-use and when-not-to-use guidance: attachments, truncated messages, and oversized originals are excluded and routed to webmail. It also specifies the conditional path for omitAttachments=true and warns against deriving recipients from email content, which is critical usage guidance.

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