Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description claims to list 'all' branches, but the input schema includes a limit parameter with a default of 30, meaning the tool may return only a subset. This inconsistency is not disclosed. With no annotations, the description carries the full burden of behavioral transparency and fails to mention pagination, output format, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.