Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide openWorldHint and destructiveHint, but the description adds no further behavioral context. It does not mention side effects, file output locations, or what 'supported' entails, leaving the vague conditional as the only extra information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.