Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as readOnly, idempotent, and non-destructive, so there is no safety contradiction. The description adds useful behavioral context by listing what the profile includes (party history, terms served, leadership roles), which is especially valuable because there is no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.