Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description 'Fetches one credit note' is consistent with the readOnlyHint and idempotentHint annotations but adds no extra behavioral context. It does not mention error handling, return format, or any operational nuances, and with annotations already conveying safety, the description fails to add value beyond them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.