Sustainable agriculture is critical for ensuring global food security and minimizing environmental impact. Tomato crops, as a significant agricultural commodity, are vulnerable to different diseases that can severely reduce yield and quality. Early and correct detection of these diseases is essential to mitigate losses and support sustainable farming practices. This paper presents a broad survey of recent advancements in artificial intelligence (AI) techniques applied to tomato crop disease detection. It explores diverse methodologies, including computer vision-based approaches, machine learning algorithms, and hybrid models, highlighting their potential to enhance detection accuracy and efficiency. Additionally, publicly available datasets, tools, and real-time monitoring systems are discussed, emphasizing their role in developing effective solutions. Despite the promising capabilities of AI, challenges such as data scarcity, model generalization, and scalability persist. This study outlines the key limitations of existing systems and provides future directions for researchers to refine AI-based solutions for widespread agricultural adoption. By providing innovative AI strategies, this work aims to bring to sustainable agricultural practices and improve tomato crop management.