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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the item goes to the recycle bin and remains recoverable for the tenant's retention window, which materially changes how an agent should reason about reversibility. It stops short of stating permission requirements or behavior on non-empty folders.

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 sentences, zero redundancy, and the operation is front-loaded ahead of the recoverability note and the caution. Every sentence carries distinct information (action, consequence, advice).

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 two-parameter destructive tool whose annotations already flag destructiveness and which has no output schema, the description covers the essentials: what is deleted and that it is recoverable. Remaining gaps are permission requirements and handling of non-empty folders, which are useful but secondary.

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 50% – mailbox is well documented but itemId has no description at all. The description's 'file or folder' phrasing gives a faint hint that itemId may reference either type, but it adds no format, ID-source, or resolution guidance to compensate for the undocumented required identifier.

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 ('Delete a OneDrive file or folder') and names the target scope, so it is immediately distinguishable from sibling deleters such as delete_gdrive_item, delete_mail_folder, and delete_outlook_task. No ambiguity about what is being operated on.

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?

Offers one piece of actionable guidance ('still worth confirming with the user first'), which is real usage advice for a destructive operation. However, it never names an alternative (e.g., move_onedrive_item or unshare_onedrive_item) or states when deletion is inappropriate, so the routing guidance is implied rather than explicit.

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