create_draft

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

The description goes beyond annotations by explicitly stating that the draft is not sent and that sending requires user confirmation in Outlook. Annotations only indicate readOnlyHint=false, which is vague. This behavioral detail is crucial for an agent to avoid assuming the email is sent, so the description adds meaningful value.

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 concise sentences that front-load the primary action ('create a draft') and immediately clarify the non-sending behavior. Every word adds value, with no redundant phrasing.

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 simple tool with three clearly documented parameters and no output schema, the description covers the essential behavioral context (draft, no send). It does not mention return values or error conditions, but these are not strictly required for calling the tool correctly given the lack of an output schema. The description is sufficiently complete for the tool's simplicity.

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 100% with descriptions for all three parameters, so the schema already documents the parameters well. The description does not add any extra meaning about parameter syntax or semantics, so it stays at the baseline of 3.

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 states a specific verb ('create') and resource ('email draft'), and clarifies that it is saved to drafts and not sent. This distinguishes it from the sibling create_reply_draft, which is for replies, by emphasizing 'new email draft'. The purpose is unambiguous and well-scoped.

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 clearly conveys the tool's use case (creating a draft) and implicitly distinguishes it from reply drafting, but it does not explicitly mention alternatives or conditions for when not to use it. It provides clear context without explicit exclusions, so it earns a 4 rather than a 5.

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