Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide minimal behavioral info (readOnlyHint=false, destructiveHint=false, etc.), so the description carries the burden. It discloses that the tool performs a locking operation and returns specific data. It does not explain the nature of the lock (temporary? charged?), potential side effects, or error conditions. Adequate but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.