Building applications composing perceptive services in a pervasive environment can lead to an inextricable problem: they were built by several people, using different programming languages and multiple conventions and protocols. Moreover, services can be volatile, so appear or disappear during running time of the application. This paper proposes the use of a dedicated human-readable semantic language to describe perceptive services. After converting this description into a more common language, one can recruit services using inference engines to build complex applications. In order to increase robustness of the whole system, descriptions of services are distributed over the network using a crosslanguage crossplateform open-source middleware of our own called OMiSCID.