Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide idempotentHint and destructiveHint, but description adds meaningful behavioral context: card details never touch Disco's servers, and the tool is a prerequisite for other operations. It doesn't fully explain whether repeated calls with different IDs attach multiple methods, but no annotation contradiction exists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.