Send New Inbox Email

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

Annotations declare destructiveHint=true and openWorldHint=true; the description goes well beyond them by disclosing that a real email is sent immediately and cannot be recalled, that it lands in the sent folder and replies thread back, and that it is created as a draft then sent with a named-draft retry path on failure. This is exactly the extra behavioral context a mutating, irreversible operation needs.

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?

Front-loaded with Purpose and broken into bold-labeled sections (Purpose, NOT for, Returns, When to use) so an agent can scan it. It is fairly long, but most sentences carry non-redundant operational guidance; the draft-retry mechanics sentence is the only part bordering on excess.

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 9-parameter irreversible send tool with no output schema, the description supplies the return value (sent email's id), the required-field rule, the safety confirmation workflow, sibling routing, and failure recovery. An agent has everything needed to call it correctly and safely.

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%, so the schema already documents every parameter in detail (recipient limits, header restrictions, idempotency key). The description only restates that a subject and at least one of html/text are required, which is already in the schema, and adds no syntax or format meaning beyond it. Baseline 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 (send) and resource (new email from an inbox), plus the key scope detail that it starts a new thread. Explicitly distinguishes itself from reply-to-inbox-thread-email, forward-inbox-thread-email, create-inbox-draft, and send-email, so an agent can route correctly without opening schemas.

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?

Provides an explicit NOT-for list mapping each alternative use case to its correct sibling, a When-to-use section with concrete user phrasing, and a hard prerequisite (must double-check with the user and get explicit confirmation before sending). Nothing is left to inference.

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