Who can open a OneDrive file

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

Annotations already flag destructiveHint and idempotentHint, but the description goes well beyond them: anyone relying on the link loses access at once, the link cannot be restored, a dry-run result is returned without confirm:true, inherited permissions must be removed on the parent folder, owner access is immune, and removal is verified by re-reading the list. It also discloses cost (0 credits) and the prerequisite that OneDrive be connected.

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?

The default action is front-loaded and each sentence carries new information (return fields, irreversibility, edge cases, cost, prerequisite). The single-paragraph, colon-delimited run-on makes it dense to parse, which keeps it from a 5, but there is 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?

With no output schema, the description steps in to enumerate the list response fields (link URL, view/edit, scope, expiry, password, inherited) and explains that removal is verified by reading the list back. Combined with the prerequisite and credit cost, an agent has everything needed to call this correctly and interpret the result.

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 the schema baseline carries most of the load, but the description adds genuine semantics: permissionId must come from the list action, and confirm:true is what actually triggers the deletion versus a preview. It does not explain the fileId format beyond the schema's 'OneDrive file or folder id'.

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?

The description names a specific verb and resource for each mode: 'action list (default)' enumerates every sharing link and person with access to a OneDrive file or folder, and 'action remove' revokes a single permission. This is clearly distinguishable from siblings like share_onedrive_file or delete_onedrive_file, which act on the file itself rather than its permissions.

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?

It states that list is the default and remove requires permissionId taken from the list, plus a concrete when-not rule (no confirm:true means nothing is removed). It also flags the two cases where removal will not behave as expected (inherited permissions, owner access). It stops short of naming sibling alternatives such as share_onedrive_file for granting access, so it is a strong 4 rather than a 5.

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