Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide critical behavioral hints (destructiveHint: true, idempotentHint: true, readOnlyHint: false), but the description adds value by specifying that it deletes 'an existing' function, implying it requires pre-existence. It doesn't contradict annotations, and while it could mention more (e.g., permissions, side effects), it offers useful context beyond the structured data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.