Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds value beyond annotations by detailing the response contents (transaction hashes, blocks, fees, iteration steps) and listing exclusions (full payloads, API saves, contract reads). Annotations already provide readOnly=true, idempotent=true, etc., so the description enriches transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.