Summer Sale Special Limited Time 65% Discount Offer - Ends in 0d 00h 00m 00s - Coupon code: ac4s65

You are building a customer support resolution agent using the Claude Agent SDK.

Anthropic CCAR-F Full Course Access
Anthropic CCAR-F View All Questions

You are building a customer support resolution agent using the Claude Agent SDK. The agent handles high-ambiguity requests like returns, billing disputes, and account issues. It has access to your backend systems through custom Model Context Protocol (MCP) tools ( get_customer , lookup_order , process_refund , escalate_to_human ). Your target is 80%+ first-contact resolution while knowing when to escalate.

Anthropic’s tool use documentation states: “Write instructive error messages. Instead of generic errors like ‘failed’, include what went wrong and what Claude should try next.” A billing dispute agent uses lookup_order , which catches all exceptions and returns a tool_result with is_error: true and the message “Tool execution failed”. Monitoring shows two failure modes: the agent retries the identical call until hitting the turn limit, or it immediately calls escalate_to_human without trying alternative tools.

Which change follows the documented recommendation and gives Claude the information it needs to select the correct recovery action for each error type?

A.

Implement retry logic with exponential backoff inside each tool implementation so transient errors are resolved transparently within the tool before any failure result is surfaced to Claude in the agentic loop.

B.

Return error-type-specific messages with is_error: true , e.g., “Order not found—try get_customer to search by phone” for data errors and “Database timeout (transient)—retry should succeed” for infrastructure errors.

C.

Remove is_error: true and return the error details as normal tool content, so Claude reasons about the response as data rather than treating it as a flagged failure condition that biases retry behavior.

D.

Add an error classification step in the agentic loop that intercepts tool errors before Claude sees them, then routes to hardcoded retry or escalation logic.

CCAR-F PDF/Engine
  • Printable Format
  • Value of Money
  • 100% Pass Assurance
  • Verified Answers
  • Researched by Industry Experts
  • Based on Real Exams Scenarios
  • 100% Real Questions
buy now CCAR-F pdf
Get 65% Discount on All Products, Use Coupon: "ac4s65"
Next
You are building a structured data extraction system using Claude.
You are using Claude Code to accelerate software development.
Previous