create_reply_draft

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

With no annotations, the description carries the burden and does disclose the crucial non-sending, human-review behavior. It omits whether it produces a reply vs reply-all, and whether existing draft conflicts overwrite anything.

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?

Two compact sentences, front-loaded with the action and immediately followed by the non-send caveat. 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 simple 2-param tool with no output schema this is nearly adequate, but the undefined 'comment' parameter and no guidance on return value or draft location leave a real gap.

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 0%, so both parameters are undocumented in structured data. The description explains message_id accepts 'ref or raw id', but the 'comment' parameter is never mentioned, leaving its role (reply body?) entirely unclear.

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 a draft reply to a message') with an explicit parenthetical on id format. It is distinguishable from create_draft, though it doesn't explicitly contrast with that sibling.

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 clause 'Does NOT send it; a human reviews/sends from Outlook' implies this is the right choice when you want a human-gated reply rather than a send. However, it never explicitly says when to use this versus create_draft or which message types are eligible.

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