Send or draft a message

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

Adds real context beyond annotations: a draft still prompts for confirmation because the identical call with mode='send' would deliver it, and attachments are local filesystem paths. That explains the destructiveHint=true profile in a way the annotation alone cannot. It still leaves the roles of confirm, dry_run_only, request_key, and identity_id undisclosed for a mutation tool with 17 parameters.

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?

Front-loads the core contract in the first sentence and uses backticked parameter names to keep mode/reply semantics scannable. Dense but every sentence carries information; the only soft spot is the abrupt 'Recipients are one address per list entry' fragment.

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?

An output schema exists, so return values need no explanation, and the mode/threading story is complete. The gap is parameter breadth: for a 17-parameter, destructive, open-world tool with zero schema descriptions, the description leaves too many knobs (confirm, dry_run_only, identity_id, delivery_format, custom_headers) undefined for an agent to invoke confidently.

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?

Schema description coverage is 0%, so the description carries the full burden. It adds genuine meaning for the highest-risk parameters — 'to' takes one address per list entry, 'attachments' are local file paths, 'mode' has three distinct outcomes, 'reply_to_message_id' threads under an existing message. But roughly a dozen parameters (confirm, dry_run_only, identity_id, request_key, custom_headers, return_receipt, delivery_format, priority, is_html, cc/bcc) get no semantic help at all.

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?

States a concrete verb and resource ('Write a message') and immediately pins down the default behavior (saves a reviewable draft) versus the send path. It also differentiates itself from the sibling mail_reply by name, so an agent can pick between them without opening either schema.

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?

Gives explicit mode semantics (draft default, 'send' delivers, 'later' queues to Outbox) and names the alternative for threading: 'mail_reply is usually what you want, since it also quotes.' It does not address when to prefer mail_draft_save, mail_draft_update, or mail_draft_send, which overlap with this tool's draft paths.

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