A lot of the feeling about him is correlated with how one feels about math. Those feelings range from Robert Lucas (quoted by Tyler Cowen and elsewhere):
I internalized its view that if I couldn't formulate a problem in economic theory mathematically, I didn't know what I was doing. I came to the position that mathematical analysis is not one of many ways of doing economic theory: It is the only way. Economic theory is mathematical analysis. Everything else is just pictures and talk.
Rather than following Mises's Human Action, the economics profession went the path of Samuelson's Foundations. Formalism was intereprted as synonymous with logical rigor, and in the subsequent decade positivistic testing was interpreting as synonymous with empirical analysis. By the 1960s, formalism and positivism transformed the science of economics so that the Misesian understanding of "theory" and "history" was actually completely dismissed as a relic of a pre-scientific age.
...We must always remember that Samuelson was the great anti-Misesian of 20th century economics, and in my book that translates into a force for anti-economics despite all the scientific accolades, awards, honorary degrees, and reverence by his peers
"Like herpes, math is here to stay," he said. "It takes strong math to defeat misleading math...But it does lead to a communication problem. The number of people who can communicate effectively, like Paul Krugman, is very small. I will say something. It won't be a new John Kenneth Galbraith who cleans of the Aegean stables of economics. I think that the big changes in economic doctrines which will be used in the twenty-first century will come from inside the profession."
One may choose to be agnostic on this issue. I myself am pessimistic that there is a methodogical cure for economics. I would say that prior to Samuelson's formalization in economics, there were a lot of papers published that lacked clarity and insight. Now that formalization dominates, we also see a lot of papers that lack clarity and insight. If you compare the most insightful mathematical papers with the average non-mathematical papers, math wins. But one can also run the comparison the other way and reach the opposite conclusion.
To say, as Samuelson did, that change will come from the inside the profession is to predict that change will come from those with a vested interest in the status quo. That strikes me as implausible. Change will come from the fringes of the profession, not from the center. If it comes at all.