outlook_create_draft

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

With no annotations, the description must carry the behavioral burden; it does disclose the key trait that no send occurs and that reply mode auto-populates to/subject. But it omits where the draft lands (Drafts folder), permission requirements, and error behavior, leaving meaningful gaps for a mutation tool.

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 tight sentences, front-loaded with the core action and the send-suppression constraint, followed by conditional reply behavior and the chaining hint. No wasted words.

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?

Since there is no output schema, the description should ideally mention the returned draft identifier needed to chain into outlook_add_attachment, which it only implies. Otherwise it covers creation, reply mode, and the attachment handoff adequately for a 9-param optional-everything tool.

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 all nine parameters are already documented in the schema. The description reinforces replyToMessageId semantics and auto-population but adds little beyond what the schema descriptions state, 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?

States a specific verb and resource ('Create an email draft') and immediately scopes it against the send path ('without sending'), which distinguishes it from outlook_send_email. The reply-draft variant is also differentiated from plain reply tools by noting thread preservation.

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?

Clearly signals the create-without-send context and gives explicit follow-up guidance ('Use outlook_add_attachment afterward'). However, it never explicitly names outlook_send_email or outlook_reply_to_email as the alternatives or states when to prefer creating a draft over sending directly.

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