We give the theoretical foundations and empirical evaluation of a planning agent, SHOP, performing \htn planning in a multi-agent environment. SHOP is based on \ashop, an agentized version of the original SHOP \htn planning algorithm, and is integrated in the IMPACT multi-agent environment. We ran several experiments involving accessing various distributed, heterogeneous information sources, based on simplified versions of noncombatant evacuation operations, NEO's. As a result, we noticed that in such realistic settings the time spent on communication (including network time) is orders of magnitude higher than the actual inference process. This has important consequences for optimizations of such planners. Our main results are: (1) using NEO's as new, more realistic benchmarks for planners acting in an agent environment, and (2) a memoization mechanism implemented on top of SHOP, which improves the overall performance a lot. (Also UMIACS-TR-2002-13)