A central problem in software maintenance is change propagation: given a set of primary changes that have been made to software, what additional secondary changes are needed? Although many approaches have been proposed, automated change propagation is still a significant technical challenge in software engineering. In this paper we report on an evaluation of an agent-based approach for change propagation that works by repairing violations of well-formedness consistency rules in a design model. The results have shown that given a reasonable amount of primary changes, the approach is able to assist the designer by recommending feasible secondary change options that match the designer's intentions.