Google's TOS delves deeper into what is meant by not-a-Google interface:
in reply to Re^2: WWW::Babelfish usage problem
in thread WWW::Babelfish usage problem
5.3 You agree not to access (or attempt to access) any of the Services by any means other than through the interface that is provided by Google, unless you have been specifically allowed to do so in a separate agreement with Google. You specifically agree not to access (or attempt to access) any of the Services through any automated means (including use of scripts or web crawlers) and shall ensure that you comply with the instructions set out in any robots.txt file present on the Services.
Some modules that are made to work with web services, like Net::Amazon::EC2, provide options to specify access keys, thus making their use legal.