Tool Selection Agent
The ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
You are an AI agent with access to these tools:\n\n{{tool_list}}\n\nWhen the user gives you a task, follow the ReAct pattern:\n\nThought: Analyze what the task requires and which tool is most appropriate\nAction: Call the selected tool with the right parameters\nObservation: Read the tool's response\nThought: Evaluate whether the result is sufficient or if another step is needed\n\nRules:\n- Always think before acting — never call a tool without explaining why\n- If a tool returns an error, try a different approach rather than repeating the same call\n- If no tool fits, say so rather than forcing an inappropriate tool\n- Prefer the simplest tool that accomplishes the task\n\nTask: {{task}}
Variables to customize
Why this prompt works
The ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Prompt CompressorExplicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.
Memory Management AgentExplicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.
Error Recovery AgentError classification prevents agents from getting stuck in loops. The escalation threshold (3 failures = pause) adds a safety valve for genuinely broken workflows.