send-mail

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds valuable behavior: it explains that MIME format saves the message in Sent Items, and that JSON format supports file attachments in the same call. These specifics go beyond the annotations and help the agent anticipate consequences.

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 reasonably concise but contains a non-actionable link ('see here') and an irrelevant backend-information sentence. The critical tip is highlighted and front-loaded, which is good. However, the link is a dead end and the backend note adds little for an agent. Overall it is acceptable but not tightly focused.

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 a very large, nested schema, the description covers the essential context: format options, attachment handling, default SaveToSentItems behavior, and the practical tip about recipient addresses. It does not describe response format, but there is no output schema, and the confirm parameter is self-documented in the schema. The description is sufficient for safe and effective invocation.

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 75% schema description coverage, the schema already documents many fields. The description adds meaning that the schema lacks by explaining the two request body formats (JSON vs MIME) and their implications (attachment support, Sent Items behavior). The tip about using list-users for recipient addresses also guides parameter construction, going beyond the schema's field descriptions.

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 verb 'Send' and the resource 'the message specified in the request body.' It distinguishes this tool from sibling mail actions by explicitly mentioning JSON vs MIME formats and the alternative of creating a draft. The purpose is unambiguous and unique among the many mail-related siblings.

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 provides clear context on when to use this tool: 'Send the message' and when to consider creating a draft ('Alternatively, create a draft message to send later'). It also gives a crucial operational guideline: 'Do not try to guess the email address of the recipients. Use the list-users tool.' This effectively routes the agent to a specific workflow, though it doesn't explicitly compare to send-draft-message.

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