Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. 'List all AP groups' implies a read-only operation and tells the agent there is no filtering (all groups are returned). However, it does not explicitly confirm safety, auth requirements, or potential rate limits, leaving some ambiguity for a simple list tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.