Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, open-world false, and non-destructive hints. The description adds context by mentioning the tool is free, lists specific return fields (price, payTo address, network), and implicitly clarifies it provides pricing info without side effects. This goes beyond annotation basics, though it doesn't detail response format or edge cases, explaining the 4 rather than 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.