send_message

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

With no annotations available, the description carries the full burden and does a strong job: it discloses the non-sending preview, the required commit token flow, the Sent-folder copy, and the local-path requirement for attachments. It omits some details like error behavior and token expiration, but the critical behavioral traits are transparent.

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?

Three tight sentences with no filler. The most important behavioral caveat, the preview-then-commit sequence, is front-loaded, and each sentence contributes unique information.

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 a tool with no output schema and no annotations, the description covers the full calling protocol, side effects, and the token requirement. Minor gaps remain around exact preview return structure, error cases, and account selection, but an agent has enough to invoke it 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?

Schema coverage is 0%, so the description must compensate. It adds meaningful semantics for attachments, commit, confirmation_token, and 'identical arguments'. However, most parameters like to, cc, bcc, body, html_body, and account are left to inference from their names.

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 as 'Send a new mail' and adds the two-call preview/commit behavior. The word 'new' distinguishes it from reply_to_message, though it does not explicitly name alternatives like create_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?

The description gives concrete procedural instructions: first call previews and returns a token, second call with commit=True actually sends. However, it does not explicitly say when to prefer this tool over siblings such as create_draft or reply_to_message, or when not to use it.

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