Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide strong behavioral hints (readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: true), so the bar is lower. The description adds minimal context by specifying it's a GET operation, which aligns with read-only behavior. However, it doesn't disclose additional traits like authentication requirements, rate limits, or what 'root access' entails in this system. No contradiction with annotations exists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.