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

No annotations are provided, so the description carries the full behavioral burden — and it does so well. It discloses the non-sending behavior, the human-in-the-loop flow, and the conditional behavior when sending is disabled. It omits return values and failure modes, but the critical behavioral traits are clearly stated.

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 sentences with zero waste. The primary behavior is front-loaded in sentence one, sentence two clarifies the human-in-the-loop flow, and sentence three adds a distinguishing condition. Every sentence earns its place.

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?

The core decision (draft vs send) and the sending-disabled scenario are well covered, but with no output schema, no annotations, and 71% of parameters undocumented, an agent is left without return-format guidance or parameter-level help. Adequate for the primary action, with clear gaps on operational detail.

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 only 29% (2 of 7 params documented), so the description must compensate. It adds a single parameter-relevant point — the draft lands in the mailbox — but says nothing about to/cc/bcc/subject/body semantics or formatting. This fails to offset the low coverage for a 7-parameter tool.

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 'Write a draft into the mailbox without sending it' — a specific verb and resource with the central distinction from send tools made explicit. It clearly separates this tool from siblings like send_outlook_message and send_outlook_reply by stating that the human opens and sends it themselves.

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 gives two concrete usage conditions: use this when a person needs to review/send the draft themselves, and use it when a workspace has switched sending off. It does not explicitly name alternative tools, but the draft-vs-send contrast makes the routing decision clear without requiring an agent to open other schemas.

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