gmail_send_draft

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

With no annotations provided, the description carries the full disclosure burden. It explicitly warns 'THIS SENDS REAL MAIL,' which is a critical side effect. It discloses that confirm: true is required for the actual send, that all recipients must be in allowedRecipients, and that without confirm the tool returns what would be sent and changes nothing. This is thorough transparency about side effects and prerequisites.

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, each carrying essential information: the purpose, the real-mail warning, and the conditions for sending. It is front-loaded with the action and warning, then details the requirements. While not extremely terse, there is no filler and every sentence earns its place. It could be slightly more succinct but is well structured.

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 that sends email, the description covers the critical aspects: real-world side effect, required confirmation, recipient allowlisting, and dry-run behavior. It doesn't describe the return value or error cases, but given the complexity (and no annotations), it provides enough context for an agent to call it correctly. The lack of output schema is offset by the clear behavioral notes.

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 33% (only 'account' has a description), so the description must compensate. It explains the behavior of 'confirm' clearly (true triggers send, false is a dry run) and implies that 'draftId' refers to an existing draft. It does not add format details for draftId, but the tool name and description context make it predictable. The description adds meaningful semantics beyond the bare schema, though not exhaustive.

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 opens with 'Send an existing Gmail draft,' which is a clear verb+resource combination. It explicitly states the action (send) and the object (existing draft), and distinguishes it from sibling draft tools (create, list, get, update, delete) by emphasizing 'existing' and 'real mail.' The warning about sending real Mail further clarifies the tool's unique role among the draft operations.

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 usage conditions: it requires confirm: true to actually send, and explains the allowedRecipients prerequisite for the account. It also explains the dry-run behavior without confirm. However, it does not explicitly state when to avoid using this tool in favor of a sibling (e.g., 'use update_draft to edit before sending'), so it falls short of a direct comparison, but the context is clear enough.

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