Create a draft email

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

With no annotations provided, the description must convey behavioral traits on its own. It clearly discloses that the email is not sent and is instead stored in the Drafts folder. While it does not mention potential side effects (e.g., overwriting existing drafts) or required permissions, these are not critical for a draft-creation tool. The disclosure is sufficient for a simple operation, earning a 4 rather than 3.

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?

The description is two sentences: the first states the core purpose, the second gives usage guidance. It is front-loaded and every word earns its place. No fluff or redundancy.

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?

The tool is relatively simple with six well-documented parameters and no output schema. The description provides the essential purpose and usage context. It could mention what the tool returns (e.g., draft ID) but that is not crucial for the agent's selection decision. The description covers the action, location, and when to use it, making it mostly complete for this tool's complexity.

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 100%, so the input schema already documents all six parameters (to, cc, bcc, body, subject, bodyType) with their types and semantics. The description adds no additional parameter details, but it also does not need to because the schema is complete. Baseline of 3 is appropriate.

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 action: 'Create a draft message in the mailbox's Drafts folder without sending it.' It specifies the verb (create), the resource (draft message), the location (Drafts folder), and the key distinction from sending. This unambiguously differentiates it from its sibling send_message.

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 description explicitly says 'Prefer this over send_message whenever the user should review the email first.' This directly instructs when to use this tool versus an alternative, making the usage context crystal clear.

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