mail_draft

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the description only needs to add context. It does so usefully: the operation persists a draft rather than sending it, restricts content to plain text, and constrains the sender to an enabled from_address. It says nothing about auth requirements, rate limits, or which folder the draft lands in.

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?

Four tight sentences, front-loaded with the core action and the critical "does not send" constraint, then parameter guidance. No filler, though the phrasing is terse enough that the reply guidance could be read as an afterthought.

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?

With no output schema and a single nested arguments object, the description covers what an agent needs to invoke it correctly: action, side effect, sender rules, and reply wiring. It stops short of saying what identifier is returned or where the draft is stored, which would help follow-up calls like mail_send_draft.

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 burden, and it delivers: from_address must be enabled (or omitted for the default), from_name overrides the saved sender name only for this draft, and reply_to_id should be the original message ID with explicit recipients. Only to/cc/subject/body limits go unmentioned, which is acceptable since those are self-evident.

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 specific verb and resource ("Save a plain-text iCloud draft") and immediately bounds scope with "Does not send," which cleanly separates it from the sibling mail_send_draft. An agent can pick this tool without opening any 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 concrete usage conditions: omit from_address to use the configured default sender, use from_name to override the saved sender name, and supply the original message ID plus explicit recipients for replies. It does not explicitly name the send alternative (mail_send_draft), so routing is implied rather than spelled out.

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