Send or draft a message

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

Annotations already indicate this is a write operation with potential destructiveness. The description adds valuable context about the draft confirmation behavior, the 'send' and 'later' modes, and the fact that attachments are local file paths. 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 concise at 6 sentences, front-loading the key behavior before diving into details. Every sentence adds value, though some could be more efficient. No fluff.

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?

While the description covers the core workflow and highlights the most important parameters, it omits many details about optional parameters and does not describe the output schema or error conditions. Given the tool's complexity (16 params) and the existence of an output schema, the description is moderately complete.

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 description explains only 4 of 16 parameters ('to', 'attachments', 'mode', 'reply_to_message_id'), leaving the remaining 12 (including 'cc', 'bcc', 'priority', 'is_html', etc.) entirely unexplained. Given 0% schema description coverage, the description should compensate more thoroughly.

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 'Write a message' and explains the three modes (draft, send, later), explicitly distinguishing from the sibling tool 'mail_reply' which is recommended for replying with quoting. The verb+resource is specific and the scope is well-defined.

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?

The description provides explicit guidance for when to use 'mail_reply' instead for replying with quoting. It also explains the default draft behavior and the 'later' mode. While it doesn't exhaustively cover all alternatives, it gives clear context for the primary use case and one key sibling distinction.

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