Remember, Meta-analysis, when done correctly, is just a synthesis of current evidence as PaulBrown describes. It should state the current environment of the issue or intervention, changes in the field and gaps in knowledge. The Campbell and Cochran collaboratives have “ongoing” meta-analyses where, for important evidence that clinical societies regularly refer to, they essentially recreate the initial meta-analysis, state any changes in the literature and whether gaps have been addressed and how well.
To get at PaulBrown’s question, if its important about every 3-5 years, even for well established evidence (aspirin and cardiac risk for example).
Also, if the meta-analysis and review don’t follow PRISMA guidelines, don’t waste your time. Meta-analyses has become somewhat of a cottage industry of late and fodder for publication bloat.