Question 32
An Agent SDK support agent handles returns, billing disputes and account issues through MCP tools like get_customer, lookup_order, process_refund and escalate_to_human. It aims to resolve most cases on first contact — and to know exactly when to hand off to a human.
Read the full scenario lessonProduction logs reveal inconsistent error handling: when lookup_order fails, the agent sometimes retries 5+ times (wasteful when the order ID doesn’t exist), sometimes escalates immediately (premature for temporary network issues), and sometimes asks users for clarification (inappropriate when the issue is a backend permission error). Investigation shows your MCP tool returns uniform error responses: {"isError": true, "content": [{"type": "text", "text": "Operation failed"}]}. The agent cannot distinguish between error types. What’s the most effective improvement?