create-draft-email

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

Annotations already indicate mutation (readOnlyHint=false, idempotentHint=false), but the description adds context beyond them: it clarifies the draft is stored in the Drafts folder and that no sending occurs. It also notes the approval requirement for the follow-up send action. No contradiction with annotations.

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. The most important behavioral fact ('Does NOT send anything') is front-loaded, and the alternative is named in the second sentence. Every part 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?

Given the schema covers params well and annotations exist, the description is largely complete for selection and invocation. It could mention what the tool returns (e.g., draft ID) since there is no output schema, but that gap is minor for a create-draft action.

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 86%, so the schema already documents most parameters. The description adds no parameter-specific meaning, but that's acceptable since the schema carries the burden. It does not need to compensate for gaps, so the baseline 3 applies.

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?

Description states a specific verb and resource: 'Create a DRAFT email in the signed-in user's Drafts folder.' It clearly differentiates from the sibling send-draft-email by emphasizing it does NOT send anything. This is a precise, distinguishable purpose.

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?

Explicitly tells the agent when not to use this tool ('Does NOT send anything') and names the alternative ('use send-draft-email') with a condition ('with explicit user approval'). This is direct, actionable routing guidance.

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