Anthropic’s tool use documentation states: “Write instructive error messages. Instead of generic errors like…

Question

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?

Accepted Answer

D. 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.

Answer

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.

Answer

B. Add an error classification step in the agentic loop that intercepts tool errors before Claude sees them, tags each as “retry,” “try_alternative,” or “escalate,” and appends that recommendation to the tool result.

Answer

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.

Question 49