Phase 2: Tool Design & Function Calling · 55 min · Python · asyncio · Tenacity

Error Handling in Tool Execution

An agent that crashes is useless. An agent that handles errors gracefully is production-ready.

Hiring signal: Production agents fail — APIs go down, rate limits are hit, data is missing. Engineers who have built resilient tool executors and can explain their error taxonomy and retry strategy are demonstrably experienced with production systems. This is a common system design interview topic: 'How would you handle API failures in your agent?'

What you will learn

Implement retry logic with exponential backoff for transient failures
Return structured error information to the model so it can reason about failures
Design fallback strategies: cached data, degraded responses, graceful escalation

The Problem

An agent calls your get_flight_prices tool. The airline API is down. Without error handling, the agent crashes and the user sees a 500 error. With good error handling, the agent catches the failure, explains it to the model, and the model responds: "I couldn't retrieve live prices right now — here's what I know from cached data." The agent loop continues. The user experience is preserved.

The difference isn't in the model — it's entirely in how your tool executor handles failures.

Error Taxonomy for Tools

Not all errors are created equal. The correct response depends on the error type. Build your tool executor around this taxonomy:

Error Type	Example	Correct Response
Transient	429 rate limit, 503 temporary outage, network timeout	Retry with exponential backoff
Client error	400 bad input, 401 unauthorized, 404 not found	Return structured error, let model handle — do NOT retry
Partial success	Got 3 of 5 records before timeout	Return what you have with a `partial_response` note
Unrecoverable	Implementation bug, data corruption, 500 internal error	Surface to human, do not retry

The most important distinction: transient errors should be retried; client errors should not. Retrying a 404 wastes time. Retrying a 429 without backoff makes your rate limit problem worse.

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers Retry Patterns, Returning Errors to the Model, Build It, What to Practice — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.

Key terms in this lesson

Agent