There is evidence that adding motion-tracked avatars to virtual environments increases users’ sense of presence. High quality motion capture systems are cost sensitive for the average user and low cost resource-constrained systems introduce various forms of error to the tracking. Much research has looked at the impact of particular kinds of error, primarily latency, on factors such as body ownership, but it is still not known what level of tracking error is permissible in these systems to afford compelling social interaction. This paper presents a series of experiments employing a sizable subject pool (n=96) that study the impact of motion tracking errors on user experience for activities including social interaction and virtual object manipulation. Diverse forms of error that arise in tracking are examined, including latency, popping (jumps in position), stuttering (positions held in time) and constant noise. The focus is on error on a person’s own avatar, but some conditions also include error on an interlocutor, which appears underexplored. The picture that emerges is complex. Certain forms of error impact performance, a person’s sense of embodiment, enjoyment and perceived usability, while others do not. Notably, evidence was not found that tracking errors impact social presence, even when those errors are severe.