Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden; it does disclose the outcome (a confirmation message containing the new employee ID), which is useful. It says nothing about required permissions, validation failures (e.g. duplicate email), or whether the write is reversible — meaningful gaps for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.