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

With no annotations provided, the description carries the full burden of disclosing behavior. It covers three key behavioral traits: sending as the mailbox owner only (identity limitation), plain-text-only content with no HTML (format constraint), and the requirement for user confirmation before invocation (safety protocol). While it doesn't discuss error handling or return values, these disclosures are substantive and appropriate for a send action.

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 three sentences long, with every sentence serving a distinct purpose: first identifies the action, second identifies the sender constraint, third covers format and the confirmation requirement. The most important information (what it does, who it sends as) is front-loaded, and there is no redundant or filler content.

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 send action with no output schema and no annotations, the description covers the essential operational context: the action, identity constraints, format restrictions, and the need for user confirmation. It doesn't mention edge cases like invalid addresses or delivery semantics, but these are not critical for a straightforward email-sending tool. The description combined with the schema provides enough information for an agent to call 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?

The description adds meaning beyond the schema by clarifying the body format ('Plain text only — write real line breaks, not HTML') and the mailbox identity ('Sends as the mailbox owner and nobody else'), which are not fully captured in the schema's concise field descriptions. However, it provides no additional guidance for cc, bcc, or subject parameters, and the schema already documents to, body, and mailbox. The description partially compensates for the 50% schema coverage but leaves several parameters relying on their obvious semantics.

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 explicitly states the verb and resource: 'Send a new email from this mailbox.' It further clarifies the sending identity ('Sends as the mailbox owner and nobody else'), which distinguishes it from send_gmail_reply and create_gmail_draft. An agent can immediately understand this tool's unique role among the large sibling set.

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: it sends a new message from the connected mailbox, in plain text only, and requires explicit user confirmation ('Ask the user to confirm before calling this'). It does not explicitly name when-not-to-use alternatives (e.g., send_gmail_reply for replies), but the phrase 'new email' implies that scope and the confirmation requirement provides actionable guidance.

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