This paper describes a task-oriented approach to cope with the difference between the three dimensional (3D) space in a virtual reality (VR) system and that perceived by the user from its stereoscopic images with binocular disparity. This difference occurs for the reason that human visual perception is affected not only by binocular disparity but also by various kinds of visual cues. Although it is possible to set some of those cues consistent with each other when they are presented by a stereoscopic display, it is difficult to do the same for other cues especially vergence and focus. As the result, the users of VR systems often fail to manipulate virtual objects due to this difference. In this article, we propose to adjust the virtual space in a VR system through object manipulation by the user so that the user does not fail in each manipulation. We verified by experiments that this adjustment is effective to improve the rate of successful manipulation.