create_draft

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the side effect profile — the draft is created and is visible/unsent, so nothing is transmitted — but says nothing about permissions, whether the draft is saved to a specific mailbox, or what happens if 'from' is omitted.

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 sentences, no filler, and the core action is front-loaded ahead of the usage rule. Every clause carries 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?

For a mutation tool with no annotations, no output schema, and half the parameters undocumented, the description is adequate but leaves real gaps: no return value or draft identifier, no error behavior, and no routing to the reply/approval siblings. The safety-relevant 'unsent/visible' framing is the strongest part.

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 coverage is 50% (to and from are documented; text and subject are not), and the description contributes no parameter information at all. It neither explains the optional 'from' fallback nor the subject length constraint, so it fails to compensate for the coverage gap.

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?

Names a specific verb+resource ('Create a visible unsent draft in Apple Mail') and adds the key qualifier 'unsent' plus the visibility trait, which separates it from a silent compose. It does not, however, distinguish itself from the sibling create_reply_draft, which covers the same operation for replies.

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 a clear conditional context: 'Use this before sending whenever the user should review the message.' That is a real when-to-use rule rather than a restatement. It stops short of naming alternatives (create_reply_draft for replies, queue_email_for_approval for approval flows), so there are no exclusions.

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