Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states what the tool does, without mentioning side effects, such as whether it replaces the entire text, what happens if the node is not found or is not a text node, or whether the operation is reversible. The 'existing' hint implies a precondition but does not explain failure modes, making it inadequate for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.