create-draft

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

With no annotations, the description fully carries the behavioral burden. It discloses that the tool only creates a draft, sends nothing, and requires the user to manually send from Mail.app. It also states the return content: confirmation with recipients and attachment count.

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?

Three concise sentences, each serving a distinct purpose: usage trigger, return value, and safety/alternative. No wasted words, well-structured.

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 output schema exists and the schema covers most parameters, the description adequately covers usage, return, safety, and alternatives. It is complete enough for an agent to invoke correctly without additional context.

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 covers 57% of parameters with descriptions (cc, bcc, account, attachments). The description adds minimal semantic value beyond a redundant note that to/cc/bcc are arrays and attachments are optional. It does not clarify the unexplained required parameters, though their names are self-explanatory.

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 the tool creates an email draft for the user to review in Mail.app, using the specific verb 'composing' and resource 'draft'. It distinguishes itself from send-email by explicitly framing draft creation as the safe default, making its purpose unambiguous.

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?

Provides explicit 'Use when' and 'Do not use when' instructions, naming send-email as the alternative for confirmed sends. This gives the agent clear decision criteria for selecting this tool over siblings.

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