Originally published on AI Tech Connect.
What you need to know There is a class of agent bug that survives every review you run, because nothing about it looks wrong. The trace reads well. The model picks create_refund, which is exactly the right tool, emits valid JSON that passes the schema, and the customer gets a polite confirmation. The only defect is that the amount field says 12 and the customer, in Pune, said twelve lakh. Or the appointment lands on 4 September when a user in Leeds typed 9/4 meaning 9 April. Or the order ID is well-formed, plausible and does not exist, because the model composed it from the pattern of the last one it saw. This is argument extraction: given that the agent chose the right tool, did it fill in the right values? It is a different problem from tool selection, which is mostly won or lost in the…
Top comments (1)
A robust guardrail is to validate arguments against the user-visible source span, not merely the tool schema. Store the normalized value, the raw phrase, locale/timezone assumptions, and a confidence threshold together; ambiguous values can then trigger a targeted confirmation before any side effect.