Tool-augmented LLM agents rely on runtime filtering to decide which tools should be visible at each step. Causal Minimal Tool Filtering (CMTF) reduces tool-choice confusion by exposing only the next causally necessary tool frontier, but it assumes that the user request has already been mapped to a symbolic goal state. In practice, requests such as "handle my appointment" or "take care of this email" may correspond to multiple possible goals. This creates wrong-goal execution, where an agent follows a valid causal tool path for an unintended objective. We introduce GIST-CMTF, a goal-state inference layer that predicts candidate symbolic goals over the same state-transition vocabulary used by CMTF, estimates ambiguity, and either applies CMTF or exposes clarification as a causal action that produces missing goal or state variables. We evaluate GIST-CMTF across seven model backends, six filtering methods, and 120 controlled tool-use tasks. GIST-CMTF achieves 97.0% task success, compared with 80.1% for top-goal CMTF and 82.9% for semantic-goal CMTF. It reduces wrong-goal execution from 19.4% under top-goal CMTF to 2.5%, while preserving the one-tool exposure of causal filtering and using substantially fewer tokens than all-tools exposure. These results suggest that reliable tool-augmented agents should validate goal state, not only tool relevance, before exposing external actions.

翻译：工具增强型LLM智能体依赖运行时过滤来决定每一步应暴露哪些工具。因果最小工具过滤（CMTF）通过仅暴露下一个因果必需的工具前沿来减少工具选择混淆，但该方法假设用户请求已被映射为符号目标状态。实践中，如“处理我的预约”或“处理这封邮件”等请求可能对应多个可能目标，导致智能体在遵循有效因果工具路径时，实际执行的是非预期目标的错误目标执行。我们提出GIST-CMTF这一目标状态推理层，它可在CMTF使用的相同状态转换词汇表上预测候选符号目标，评估歧义性，随后应用CMTF或将澄清暴露为因果动作，以生成缺失的目标或状态变量。我们在七个模型后端、六种过滤方法和120项受控工具使用任务中评估GIST-CMTF。GIST-CMTF实现97.0%的任务成功率，而最佳目标CMTF和语义目标CMTF分别为80.1%和82.9%。该方案将错误目标执行率从最佳目标CMTF的19.4%降至2.5%，同时保持因果过滤的单工具暴露特性，且使用的令牌数远少于全工具暴露。这些结果表明，可靠的工具增强型智能体在暴露外部动作前，应验证目标状态而非仅验证工具相关性。