You are building a multi-agent research system using the Claude Agent SDK.

Option A defines what successful research must achieve without hard-coding a brittle search procedure. The subagent receives measurable objectives—breadth, diversity, recency, and relevance—but retains authority to reformulate queries, follow promising leads, and adjust source selection when the topic does not match familiar patterns. Anthropic’s account of its multi-agent research system states that subagents need an objective, expected output format, guidance about tools and sources, and clear task boundaries. This is more informative than option B’s vague instruction, yet more adaptive than prescribing every query. Option C improves only one known failure path and still constrains the agent to a predefined procedure that may be unsuitable for emerging subjects. Option D adds orchestration complexity and a potentially incorrect classification step without solving over-prescription within either category. The coordinator should describe mandatory constraints separately from strategic guidance: authoritative-source requirements and time boundaries can remain fixed, while query formulation and exploration paths remain agent-controlled. Evaluation should then measure source coverage, evidence quality, duplication, and discovery of relevant secondary leads rather than whether the subagent followed a particular series of searches.

================