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

Goes well beyond the annotations by disclosing the Drafts-folder destination, the Mail.ReadWrite permission requirement, and the concrete consent_required failure for accounts connected before the tool existed. One minor tension goes unaddressed: annotations set destructiveHint=true while the description frames the operation as harmless, with no explanation of what is considered destructive.

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?

Front-loaded with the selection condition, and the remaining sentences are dense with distinct facts rather than filler. It runs long as a single block, and the conditional parameter rules could be tightened, but nothing is redundant.

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?

Covers purpose, prerequisites, mode-dependent required parameters, and limitations; return values need not be explained because an output schema exists. An agent has everything needed to call it correctly on the first try.

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 per-parameter meaning is already documented; the description's added value is the two-mode model (new message: subject+body, to/cc optional; reply: reply_to_id+body only, recipients and subject inherited). That mode framing is genuinely useful, though it largely restates the schema's own 'not with reply_to_id' notes.

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 (saves an email draft in the Microsoft 365/Outlook Drafts folder) and explicitly scopes it as non-sending. Immediately distinguishes itself from m365_send_email, m365_reply_email, and the Mac Mail create_draft.

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?

Opens with an explicit triggering condition ('Use this when the user wants an email prepared... without sending it') and names the three alternatives with the condition that selects each. It also states exclusions (no attachments) and a prerequisite failure mode.

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