Parameters values of evolutionary algorithms have significant effect on the performance of algorithms. The process of parameter setting is important and this subject has been investigated in the optimization literature using different design of experiment methods, such as the Taguchi method, the full factorial design of experiment, the surface response methodology, etc. All mentioned approaches considered only the individual response variable, i.e., a performance metric for evaluating algorithm, in finding the optimal setting for the parameters. However, there are multiple performance metrics that should be taken into consideration when tuning a parameter. In this research, a new approach to tune evolutionary algorithms parameters is proposed which simultaneously optimizes all performance metrics of the algorithm and provides the optimal setting for the parameters of the algorithm. To show the application of the proposed approach, a case study is developed based on a multi-objective optimization problem. The developed problem is solved using multi-objective particle swarm optimization algorithm (MOPSO) which considers different setting of algorithm parameters, i.e., scenario, using full factorial design of experiment. In each scenario, different performance metrics are calculated as response variables. Then, the desirability function approaches are applied to provide the optimal setting of the parameters when all response variables are optimized.