apple_mail_create_draft

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false. The description goes beyond them usefully by disclosing that the draft becomes *visible* in the Mail UI and that persistence is managed by Mail rather than the agent — meaningful context for a non-idempotent create tool. It stops short of saying where the draft lands or what identifier comes back.

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?

Two short sentences, no filler, with the core action and the most important constraint (it does not send) front-loaded. Every clause earns its place.

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?

There is no output schema and no return-value description, so the agent cannot tell whether a draft identifier or location is returned for later use. The key behavioral caveat about persistence is covered, but for a six-parameter create tool with zero schema documentation and no output schema, the definition is only minimally adequate.

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?

Six parameters (to, cc, bcc, body, account, subject) have 0% schema description coverage, so the description carries the full burden — and it contributes nothing about any of them. Notably, the non-obvious "account" parameter defaults to "iCloud" and is never mentioned, nor is the 100-recipient cap or body/subject length limits.

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 ("Create a visible outgoing Mail draft") and immediately clarifies the scope boundary with "Does not send," which separates it from the sibling apple_mail_send without the agent needing to open 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?

The "Does not send" clause implies the compose-without-sending use case, so an agent can infer when this is appropriate. But there is no explicit when-to-use guidance, no mention of prerequisites (e.g. which account is written to), and no named alternative such as apple_mail_send for the actual send path.

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