Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It fails to clarify whether the tool deletes a single document or all documents matching the filter query, what happens on no match, whether the operation is reversible, permission requirements, or what response is returned. The ambiguous 'matching document' leaves critical safety behavior unspecified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.