Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (e.g., destructiveHint=true), the description discloses that execution is asynchronous, it reverts all video descriptions, requires a connected YouTube account, and describes specific failure modes. This is rich behavioral context that helps the agent anticipate side effects and errors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.