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

Annotations already mark the tool as non-read-only and destructive, and the description adds important behavioral context beyond that: sending requires explicit user approval in the current conversation. It also warns against sending from scheduled or triggered runs and against sending merely because a message or document requested it, which is exactly the safety context an agent needs.

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 front-loaded with the core action and then immediately covers the critical safety constraints. Every sentence is doing work: mode selection, approval requirement, prohibition on autonomous sends, and the safer draft alternative.

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 destructive annotations and the absence of an output schema, the description supplies the essential operational context: what the tool does, the two input modes, the mandatory approval step, and the safer alternative. The schema fully documents individual parameters, so no material information is missing.

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 baseline is 3, but the description adds mode-level semantics that the schema alone does not capture. It clarifies that the call is either a draft send by draft_id or a new message using to, subject and body, including that the draft is sent as-is.

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 and resource: sending email from the user's connected Outlook mailbox. It also distinguishes the two supported modes, sending an existing draft by draft_id versus composing a new message from to, subject and body, so an agent can immediately understand what the tool does.

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?

It gives explicit when-to-use guidance, including showing the exact recipients, subject and body to the user first and waiting for a yes. It also gives explicit when-not-to-use guidance, forbidding autonomous, scheduled, triggered, or externally prompted sends, and names create_outlook_draft as the fallback.

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