send_email

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

No annotations are provided, so the description must fully convey behavioral traits. It mentions that domain is inferred automatically from inbox_id and that both html and text can be supplied. However, it does not disclose potential rate limits, authentication prerequisites, or what happens on failure. Given the output schema exists, the description adequately covers basic behavior but lacks deeper insights.

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 front-loaded with the core purpose, followed by brief usage notes, then an Args list. It is concise and structured, with each sentence serving a purpose. The Args list could be more compressed, but it is well-organized. No redundant information.

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 has 10 parameters and an output schema, the description covers key workflows: basic send, reply to thread, and attachments. It explains domain inference. It does not cover error handling or prerequisites like domain verification, but the output schema likely provides return structure. Overall, it is sufficiently complete for typical use cases.

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 input schema has 0% description coverage, so the description must compensate. The description includes an Args list that explains each parameter's role, e.g., 'to: Recipient email address (for multiple, comma-separate)', 'attachments: Comma-separated attachment IDs from upload_attachment'. This adds significant meaning beyond the raw schema. Some param details (e.g., format of thread_id) are not specified, but overall it is helpful.

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 'Send an email message.' as the primary action, which is a specific verb plus resource. It distinguishes itself from sibling tools (e.g., create_inbox, assign_thread) by focusing on sending email. The tool's unique function is immediately obvious.

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 practical guidance on how to use the tool: it explains how to reply in a thread (pass thread_id), how to attach files (call upload_attachment first, then pass IDs), and that inbox_id is sufficient for domain inference. It does not explicitly state when not to use this tool, but given no sibling sends email, this is acceptable.

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