Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It does reveal that the tool involves an interactive sequence (paste, confirm, pick), which implies user involvement and likely prompts. However, it does not disclose side effects, whether state is modified, or what happens on completion.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.