outlook_create_draft

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

With no annotations, the description carries the full burden. It implies the tool creates a draft and does not send it (via 'Drafts folder' and 'Human-in-the-Loop review'), but it does not explicitly state that no email is sent, nor does it mention permissions, side effects, or the response format. It adds some context beyond the name but leaves gaps.

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 a single, front-loaded sentence that conveys purpose and usage context in under 20 words. Every word earns its place, with 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?

Given the tool has 5 parameters and an output schema, the description does not need to explain return values. It provides the key 'why' (HITL review) and clarifies the tool's role relative to sending. However, it lacks parameter semantics and does not mention prerequisites or error conditions, so it is not fully complete. The output schema and parameter names help, but the description could add more context.

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 0%, and the description provides no explanation of any parameters (e.g., reply_to_message_id, to_recipients). The agent must rely entirely on the schema, which does not convey the meaning or usage of each field. The description fails to compensate for the lack of parameter info.

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 action ('Create an email draft') and a specific resource ('Outlook Drafts folder'). It also distinguishes from siblings by noting this is the 'recommended method for Human-in-the-Loop review,' implying it is for draft creation rather than direct sending (e.g., outlook_send_mail).

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 phrase 'recommended method for Human-in-the-Loop review' gives clear guidance on when to use this tool (when human review is needed before sending). However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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