Congestion on roads and highways is an issue that leads to reductions in the energy-efficiency of travel. Current GPS navigation devices include features which provide turn-byturn directions to vehicles based on real-time traffic conditions, and these features provide an opportunity to improve average fuel consumption. Routing strategies in these devices optimize individual travel times, but theoretical (e.g., Braess's paradox) and empirical results show that this can actually increase congestion and average travel times. We model traffic routing in the game-theoretic framework of Stackelberg games, which is a simplification of the true information patterns, and then use this model to provide an algorithm for turn-by-turn directions. One advantage of our algorithm is that it can be easily incorporated into existing GPS devices by modifying the traffic information sent to them. Our framework is used to qualitatively study the effectiveness of traffic routing on a specific road network topology. If roughly 60% of users follow GPS directions implementing our strategy, then the average delay will be close to the optimal average delay for the road network. This poses social and technological challenges for reduction in congestion through routing. The situation is not hopeless though, because our qualitative results indicate that having a small percentage of compliant users may still lead to large reductions in congestion.