The decision provides a useful occasion to reflect on the distinction between law and policy. Judicial review of administrative action typically involves a "somewhat probing examination"* of the reasons given for a decision in an attempt to find a flaw that renders it unreasonable. A view of the merits of the underlying policy is usually unavoidable, but reviewing courts do not 'make policy'. Rather, they hold a policy up to the light of legality, comprised of statutes and other legal norms. A convincing judicial review decision will highlight logical flaws or non sequiturs that tainted the policy.
As Judge Tatel explained, writing for the majority of the Court:
Before beginning our analysis, we think it important to emphasize that although the question of net neutrality implicates serious policy questions, which have engaged lawmakers, regulators, businesses, and other members of the public for years, our inquiry here is relatively limited...[O]ur task as a reviewing court is not to assess the wisdom of the Open Internet Order regulations, but rather to determine whether the Commission has demonstrated that the regulations fall within the scope of its statutory grant of authority (slip op. at pp. 16-17).In vacating part of the Commission's Order, the Court focused on one flaw in particular. The Commission had imposed anti-discrimination and anti-blocking rules on the broadband providers. They were not to discriminate between different edge providers. This may make sense from a policy perspective: would you want broadband providers to cut sweetheart deals with Netflix but block or allocate meagre bandwidth to Youtube?
As the Court pointed out, the effect was to treat broadband providers as common carriers, like "innkeepers, ferrymen and others who [serve] the public", businesses that are to treat all-comers as equals (at p. 47). But the fatal flaw in the Commission's position was that it had chosen not to classify broadband providers as common carriers. It could not refuse in one breath to treat them as common carriers yet impose the obligations of common carriers on them in the next.
The Commission tried to avoid this conclusion by arguing that the nature of common carriage involves a relationship between a service provider and an end user. Here, it argued, it was not regulating the relationship between broadband providers and consumers of broadband internet; it focused on the intermediate relationship between the broadband providers and edge providers. Again, the Court identified a fatal flaw in the Commission's reasoning:
Because broadband providers furnish a service to edge providers, thus undoubtedly functioning as edge providers' “carriers,” the obligations that the Commission imposes on broadband providers may well constitute common carriage per se regardless of whether edge providers are broadband providers’ principal customers. This is true whatever the nature of the preexisting commercial relationship between broadband providers and edge providers. In contending otherwise, the Commission appears to misunderstand the nature of the inquiry in which we must engage. The question is not whether, absent the Open Internet Order, broadband providers would or did act as common carriers with respect to edge providers; rather, the question is whether, given the rules imposed by the Open Internet Order, broadband providers are now obligated to act as common carriers (at pp. 51-52).The case was, in the Court's view, on all fours with a Supreme Court precedent, Midwest Video II.
Whether one agrees or disagrees with the Court's conclusion, the central point is that judicial review of administrative action does not require judges to legislate or make policy. Rather, it requires them to poke and prod, to conduct a "somewhat probing examination" in order to uncover flaws in the impugned decision. The gap between "law" and "policy" is maintained by doctrine which governs how reviewing courts go about their task (and not the concepts of "law" and "policy" themselves, which are too vague as to have any practical utility in this context). Sometimes judges will overstep the mark and be subject to justifiable criticism but that seems not to have happened here.
I think much the same can be said about review of official action (including legislation) on constitutional grounds, but that is a grand claim which would require significant support.
* The description is from Canada (Director of Investigation and Research) v. Southam Inc.,  1 SCR 748. Canadian courts got dreadfully confused by treating this as a substantive test of the reasonableness of a decision rather than as a description of the process of judicial review.