This paper evaluates the effectiveness of large language models (LLMs) on the task of context-aware music recommendation, specifically focusing on the alignment of music tracks with a listening intent, in addition to user preferences. We present a preliminary investigation in which five LLMs (variants of LLama, Qwen, and Mistral) are tasked with ranking a candidate set of tracks containing both ground-truth items (associated with specific user-intent pairs) and distractor items (containing user-relevant, intent-relevant, or non-user and non-intent relevant items). Our results show that LLMs rank intent-user-relevant items higher than the distract items, with “Llama-3.1-8B-Instruct” having the best performance (NDCG of 0.320.20 vs. 0.200.15). We further investigate whether performance differs when mentioning the listening intent explicitly in the prompt vs. implicitly given solely music preferences.Surprisingly, the LLMs achieved the best performance through an implicit indication of intent, versus explicitly adding it to the prompt, with “Mistral-7B-Instruct-v0.3” performing the best (NDCG of 0.370.22 vs. 0.290.18).