mail_send_email

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

The description discloses that html_body is passed verbatim without sanitization and includes a security warning about prompt injection, which is critical behavioral context. However, it does not mention other behaviors like authentication requirements or success/failure responses, leaving some gaps.

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 succinct, front-loaded with the purpose, and structured as a clear 'Args:' list. Every sentence is necessary, including the security note, making it an efficient reference.

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 an output schema exists, the description appropriately omits return values. It covers purpose, parameters, and a security warning. However, it lacks context on error conditions, rate limits, or required permissions, but these are partially offset by the output schema.

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?

With 0% schema description coverage, the description compensates by explaining each parameter (e.g., 'Optional HTML body content... Passed verbatim...,' 'auto-selects first identity if omitted'). This adds value beyond the schema's field titles and types.

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 states 'Send an email via Fastmail,' clearly indicating the tool's verb and resource. While it doesn't explicitly differentiate from siblings like mail_forward_email or mail_reply_to_email, the name and description imply it's for composing and sending a new email, which is distinct.

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?

No guidance is provided on when to use this tool over alternatives such as mail_forward_email or mail_reply_to_email. There are no exclusions or context about prerequisites, making it less helpful for an AI agent to decide between tools.

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