You are building a Mosaic AI agent for a retail customer-support app. The agent has access to a tool `issue_refund(order_id, amount)` that calls an internal API to process a monetary refund. During testing, you notice that when the LLM's reasoning loop occasionally re-invokes the same tool call after a transient response parsing error, customers are sometimes refunded twice for the same order. Which design change most directly prevents duplicate side effects from repeated tool invocations?