Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and non-destructive, and the description adds substantial behavioral detail beyond that: liquidity gates, the ±40% cap, median consistency checks, real same-card/same-grade moves, and a 20-card limit. This meaningfully informs the agent about result trustworthiness and constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.