send-email

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

Disclosures beyond annotations: destructiveHint is elaborated as 'sends external comms', and the description details pre-send validation, failure conditions (allowlist), and that returns a confirmation ID. No contradiction with 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?

The description is a single, dense paragraph with key information front-loaded. It efficiently covers the main action, safety options, constraints, and alternative workflows, though minor restructuring could improve readability.

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?

Given the tool's complexity (safety checks, rate limits, allowlists) and sibling tools for drafted emails, the description covers all major aspects: immediate send, safety modes, constraints, and alternative draft workflow. Missing a detailed return shape, but no output schema exists.

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?

Input schema has 100% description coverage, but the description adds value by explaining the interaction between dryRun and checkRecipients and noting that comma-separated strings or arrays are accepted for recipient parameters.

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 tool composes and sends an email immediately, highlighting its destructive nature and returning a confirmation ID. It distinguishes from sibling tools like 'draft' by noting when a multi-step workflow is preferred.

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?

Explicitly provides safety controls (dryRun, checkRecipients) and when to use them. Mentions rate limits and recipient allowlist constraints, and advises using 'draft' for multi-step workflows instead of direct sending.

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