可靠的多轮工具调用要求智能体持续维护一个动态演化的任务状态，并确保每一步动作均与该状态保持一致。然而，直接函数调用（direct function-calling）和 ReAct 风格策略将状态跟踪与动作生成耦合于同一自回归序列中，由此引发状态—动作竞争：生成下一调用的压力可能覆盖或忽略交互早期积累的信息。受博伊德（Boyd）观察—判断—决策—行动（Observe-Orient-Decide-Act, OODA）循环启发，我们提出 OODA-Tool——一种类型化、闭环的策略，通过分离状态维护与动作实现来缓解该竞争。OODA-Tool 并非直接从交互历史生成动作，而是将每次决策经由控制器校验的中间状态进行路由，从而确保最终输出始终锚定于当前任务状态。具体而言，Observe 阶段重建任务状态，Orient 阶段判定是否需执行，Decide 阶段构建合法的动作结构，Act 阶段实现外部输出。我们在多轮、多工具及信息不完整等设定下，使用参数量从 0.6B 至 14B 的 Qwen3 模型，将 OODA-Tool 与直接函数调用及 ReAct 策略进行对比评估。结果表明，OODA-Tool 在所有模型规模上均稳定提升任务成功率，且在较小模型以及动作高度依赖跨轮次累积信息与先前工具结果的任务上增益更为显著。控制变量实验、阶段级消融分析及迁移评估进一步验证了这些改进的鲁棒性。

Reliable multi-turn tool use requires an agent to preserve an evolving task state and ensure that each action remains consistent with it. However, direct function-calling and ReAct-style policies learn state tracking and action generation within the same autoregressive trajectory. This coupling creates state-action competition: the pressure to produce the next call can overwrite or ignore information accumulated earlier in the interaction. Inspired by Boyd's Observe-Orient-Decide-Act cycle, we introduce OODA-Tool, a typed closed-loop policy designed to mitigate this competition by separating state preservation from action realization. Rather than generating an action directly from the interaction history, OODA-Tool routes each decision through controller-checked intermediate states, ensuring that the final output remains grounded in the current task state. Specifically, Observe reconstructs the task state, Orient determines whether execution is warranted, Decide forms an admissible action structure, and Act realizes the external output. We evaluate OODA-Tool against direct function-calling and ReAct policies using Qwen3 models ranging from 0.6B to 14B across multi-turn, multi-tool, and incomplete-information settings. OODA-Tool consistently improves task success across model sizes, with larger gains on smaller models and on tasks whose actions depend strongly on information accumulated across turns and prior tool results. Controlled variants, stage-level ablations, and transfer evaluations further demonstrate the robustness of these improvements.