Relevant Is Not Always Useful: Task and Information Dependence of Guidance for LLM Agents

Natural-language instructions can improve LLM agents without parameter updates, but their value varies across tasks and information conditions. Existing approaches emphasize retrieving relevant guidance, leaving unclear whether it fits the task's execution demands and remains useful given what the agent already knows. We propose an evaluation framework that measures changes in task success against control instructions matched in length and format. Our central insight is that guidance must both fit the task and address an unresolved need; otherwise, it can prescribe unsuitable or unnecessary actions. We test these two factors through task-family comparisons, information and search-order interventions, and selective-delivery experiments. In ALFWorld, the same guidance changes from a $22.33$-percentage-point benefit with irrelevant information to a $12.67$-point loss with known target location, a $35.00$-point reversal. This pattern recurs in two additional model configurations. Search-order interventions support this explanation, while independent selection gains remain uncertain. These findings motivate evaluating guidance jointly against task demands and the agent's available information, rather than task relevance or instruction adherence alone. Code and data are available anonymously at https://anonymous.4open.science/r/review-code-anon.