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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation/safety profile is covered structurally. The description usefully distinguishes two modes (per-user revocation vs link removal), but says nothing about permission prerequisites, reversibility, or whether other shares are affected.

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 tight sentences, front-loaded with the action, followed by the lookup hint. 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?

No output schema exists, so return behavior needn't be described, and annotations carry the safety profile. However, for a destructive permission operation the description omits prerequisites (e.g., needing owner rights) and leaves itemId semantics unaddressed.

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 only 33% (mailbox documented, itemId and permissionId bare). The description compensates for one gap by telling the agent where to obtain permissionId (list_onedrive_permissions), but itemId remains unexplained in both description and schema.

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+resource ('take away access' / 'remove sharing link') on a OneDrive item, which is distinct from the sibling unshare_gdrive_item. It does not explicitly name a sibling to disambiguate against, so it stops short of a 5.

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?

Gives clear context for when to use it: revoking one person's access OR removing a sharing link, and directs the agent to list_onedrive_permissions for the required permissionId. No when-not-to-use guidance or mention of the GDrive counterpart, so not a 5.

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