Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the agent knows this mutates editor state without destroying data and is not repeatable-safe. The description adds the 'from the active project' scoping constraint, which is useful, but says nothing about what opening does to prior editor state or whether the library must already exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.