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

With no annotations, the description carries the load and does well: it discloses the immediate, irreversible effect ("the old link stops working at once"), that reversibility requires a new link rather than restoring the old one, and that the call is free. It omits whether ownership or admin permission is required and whether the call errors on an unshared folder.

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 clauses, each earning its place: the action, the effect, and the recovery path, with endpoint mapping and cost trailing. The consequence is front-loaded where an agent will see it.

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?

An output schema exists, so return values need no explanation, and the description covers the mutation's effect and how to undo it. For a destructive-without-annotations tool, the remaining gap is auth/permission expectations and error behavior on an unshared folder.

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 50%: folder_id is documented in the schema, but api_key has no description anywhere. The description never mentions either parameter, so it does not compensate for the uncovered one or clarify that folder_id must identify a folder the caller owns.

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 ("Turn a folder's share link off") and immediately names the sibling that does the inverse (share_folder). An agent can distinguish unshare_folder from share_folder and get_shared_folder without opening a 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?

Implies the use case (revoking an existing share link) and gives the follow-up path: "share_folder again makes a new one." It names the equivalent REST endpoint, which helps agents map to known API semantics. It stops short of explicit when-not-to-use conditions, such as what happens when the folder was never shared.

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