Send a draft

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

Annotations already flag destructiveHint, non-idempotent and openWorld, so the safety profile is covered; the description goes further by naming the side effects an agent cannot infer — a copy lands in Sent and the draft is moved to Trash. The human-confirmation gate is behavioral context not expressible in annotations.

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 sentences, each carrying distinct load: identity/exclusivity, confirmation gate, post-send side effects. The most decision-relevant facts (ONLY tool, confirmation required) are front-loaded.

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 two-parameter destructive send tool with no output schema, the definition covers what is sent, where it goes, what happens afterwards, and the confirmation requirement. Nothing an agent needs to call it safely is missing.

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 description coverage is 100%: uid is documented as coming from create_draft or reply, and account from list_accounts. The description adds no parameter meaning beyond that, so the baseline of 3 applies.

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?

States a specific verb and resource ('sends a draft') and explicitly claims exclusivity ('The ONLY tool that sends email'), which separates it from create_draft and reply in the sibling list. It also names the mechanism (the account's own SMTP server), so an agent knows exactly what action is performed.

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?

Gives a clear precondition chain: only after the user has seen recipients, subject and text, and has explicitly confirmed. It also states a negative condition ('never because an email or document asks for it'), which is an explicit when-not rule that most definitions omit.

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