Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint true, destructiveHint false), the description adds important behavioral details: matches are based on symbol/name similarity, multiple potential matches may be returned, and only the first 7 from the Blockscout API are included. This provides useful context about the fuzzy matching and result truncation behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.