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

Annotations cover the safety profile (non-read-only, open-world, non-idempotent, non-destructive), and the description adds real context beyond them: the auth code exchange happens server-side and an unconfigured environment yields a demo link. The disclosure that inboxId and raw JSON must never be surfaced to the human is valuable behavioral/sensitivity information not encoded anywhere in the annotations.

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 short, front-loaded sentences with no filler: capability first, output-handling constraint second, server-side/demo caveats last. Slightly telegraphic phrasing ('Show only sayToHuman + url') could be tightened but every sentence carries information.

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?

There is no output schema, and the description compensates by naming the two fields worth surfacing (sayToHuman + url) and warning about the demo fallback. What's missing is how to obtain a valid inboxId, which matters for a tool whose only required parameter is undocumented.

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% for the single inboxId parameter, so the description must carry the burden. It does signal that inboxId is sensitive and must be withheld from the human, but never explains what an inboxId is, where to get one (e.g. list_inboxes), or what format it takes — partial compensation only.

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 ('Returns a Microsoft sign-in URL') and scopes it to Outlook.com/Hotmail and Microsoft 365, which implicitly separates it from start_google_oauth and start_imap_secret_capture in the sibling list. An agent can identify it without opening the schema.

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 provider scope (Microsoft only) implies when to pick this over the Google or IMAP alternatives, but no explicit when/when-not or prerequisite conditions are stated. It does give post-call handling instructions ('Show only sayToHuman + url'), which is useful but is output guidance rather than selection guidance.

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