Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal write behavior (readOnlyHint: false), and the description's 'Save' matches that. It does not go beyond the annotation to disclose overwrite semantics, failure modes if no default path exists, or whether any confirmation is given, but for a save operation the basic behavior is clear and consistent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.