The Responsibility concept determine the expected behavior of a role and, as such, are perhaps the key concept  associated with a role. Responsibilities are divided into two types: liveness properties and safety properties .  Liveness properties intuitively state that “something good happens,” that is, describe those states of affairs that an agent must bring

about, given certain conditions.

Safety properties are invariants. Intuitively, a safety property states that “nothing bad happens,” that is, that an acceptable state of affairs is maintained. See Developing multiagent systems: The Gaia methodology (p. 344) for more information about this concept.