Large language models (LLMs) have exhibited strong semantic understanding capabilities in interpreting and reasoning for table question answering (TQA). However, they still face challenges with excessively long or complex tables, particularly when these tables are disorganized or feature hierarchical structures. To address these challenges, we propose a new paradigm for TQA, named TableCall, which leverages the tool-using capabilities of LLMs. Specifically, TableCall adapts different tools for different types of table questions, such as SQL, Python, and LLMs, to simplify and enhance the reliability of table understanding. Moreover, to further enhance LLMs’ table comprehension capabilities, we propose a few-shot library updating technique to generate more effective QA pairs to support LLM prompting. Experimental results on both open-domain and specific-domain datasets demonstrate that our approach achieves state-of-the-art performance, outperforming previous methods in terms of accuracy, efficiency, and reliability.