Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, it discloses key behaviors: the source text is cloned into the new version, the result is returned for immediate translation, and code fields must stay identical to the source. This gives the agent a clear model of what happens on invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.