Send mail

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

Beyond the destructive annotation, the description discloses the critical safety protocol: the agent must obtain explicit user approval and set confirmed=true, and never call unattended. This is essential behavioral context not captured 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?

Two sentences, front-loaded with the core purpose, and each sentence carries essential information. No redundancy.

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 10-parameter destructive tool with no output schema, the description focuses heavily on confirmation gating but omits other important aspects such as dry_run's safe preview use case, from_address alias handling, and attachment behavior. It is sufficient for avoiding misuse but incomplete for full operational understanding.

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 schema covers only 40% of parameters. The description adds meaning to 'confirmed' by tying it to the gating workflow, and references 'exact To/Subject/Body', but it does not compensate for other undocumented parameters like cc, references, in_reply_to, or attachment details. It provides some value but leaves gaps.

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?

Clearly states 'Send a new email' with a specific verb and resource, distinguishing it from sibling tools like reply, forward, and send_draft. The gated confirmation requirement further clarifies its unique behavior.

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 instructs when to use: after showing the user the exact To/Subject/Body and receiving explicit yes, then calling with confirmed=true. Also states 'Never call unattended,' providing a clear exclusion. This is strong usage guidance.

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