Reuse of existing software components can speed up software development by up to 50% [34]. However, selecting the wrong software component can lead to complications and delays—such as integration issues, performance bottlenecks, and security vulnerabilities—and often results in costly rework [5,45]. There is currently limited tool support for assessing components to make a good decision [38,45]. To address this problem, we created a prototype tool that uses natural language processing and large language models to analyze GitHub issues which we used as a corpus to create a data source of authentic communications between developers. The tool categorizes and summarizes information about software components. The prototype builds upon previous research on developers’ needs in a component selection tool [5]. In this study, we describe the tool, including reports on the tuning, and present the results of a survey of 37 participants who tested the tool, applying the critical incident technique to evaluate how effectively and accurately the proposed method provides evidence for decision-making.