Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and non-destructive behavior. The description goes beyond by disclosing the return payload (UUIDs, codes, symbols). For a parameterless list operation, this is sufficient behavioral context; no additional quirks like pagination are mentioned, but none are implied by the simple nature of the tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.