The configuration of Stingray is relatively simple. You will need two pools; one for each server. For the purposes of an example I will call them "primary" and "secondary". The "primary" pool should only contain the active server, and the "secondary" should only contain the stand-by server. Once the two pools are configured, you simply need to set the "secondary" pool as the failure pool for the "primary". Your Virtual Server should be set to use the "primary" pool as it's default traffic pool. All requests will be sent to the primary unless it fails, at which point requests will be sent to the "secondary". The servers will never be in use at the same time.
One possible issue might be with health monitoring. If you have an active health monitor on the pools, then both servers will be probed by stingray, and this traffic may hit your application (depending on the type of monitor you chose). If this is a problem, then you may need to remove all active health monitors on the secondary pool and just rely on passive monitoring there. Obviously the primary may continue to have active monitoring.
I would also double check your licensing rules to ensure that you have the correct definition of "active". Often an application is considered active if it is running, regardless of whether it is processing requests or not.
