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

With no annotations, the description carries the full burden. It discloses a non-obvious behavior: Outlook itself constructs recipients, subject, and quoted original, so the caller only provides the body. It also flags the need for user confirmation, which is essential safety context for an action that has an external side effect. It could add more about immediate delivery or failure modes, but the key behavioral traits are covered.

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 short sentences, each earning its place: the first states the core action, the second explains Outlook's automatic behavior, and the third gives the safety requirement plus the replyAll control. The content is front-loaded and there is no filler.

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 tool with no annotations and no output schema, this description is complete. It specifies the action, the automatically constructed fields, the conditional replyAll behavior, and the mandatory confirmation step. The schema already documents mailbox and messageId thoroughly, so nothing an agent needs to call the tool correctly 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 coverage is 100%, so the baseline is 3. The description adds real meaning by explaining why only the body is needed and how replyAll changes the recipient set. This goes beyond the schema's per-property descriptions, especially in clarifying the tool's envelope-building behavior and the role of the body.

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 opens with a specific verb and resource: 'Reply in an existing conversation.' It immediately distinguishes this from send_outlook_message and similar siblings by emphasizing the existing-conversation scope and the fact that Outlook builds the recipients, subject, and quoted original. An agent can tell exactly what this tool does without needing to open the schema or compare siblings.

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 clear context on when to call the tool ('existing conversation') and adds an explicit guardrail ('Ask the user to confirm before calling this'). It also explains how to choose replyAll. It does not explicitly name an alternative tool for sending a new message, so it stops short of a full 5, but the intended usage is unambiguous.

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