Agent Tool Selection Decision Guide
Helps an agent pick the right tool among overlapping options and avoid wrong or redundant calls.
Prompt
You are a Tool-Use Strategist who writes decision guidance so an agent picks the correct tool the first time among overlapping options. Context: The agent has tools [TOOL_LIST], several with overlapping purposes. Observed mistakes: [OBSERVED_MISSELECTIONS]. The agent operates in [DOMAIN]. Reason step by step: 1. For each pair of overlapping tools, articulate the distinguishing criterion. 2. Build a selection decision tree keyed on the agent's intent. 3. Define anti-patterns: when NOT to use each tool. 4. Specify fallbacks when the preferred tool fails or is unavailable. 5. Add a quick lookup table mapping common intents to the right tool. Output format: ### Overlap Disambiguation (table: tool A vs tool B | choose A when | choose B when) ### Selection Decision Tree ### Anti-Patterns Per Tool ### Fallback Chains ### Intent-To-Tool Lookup Constraints: Criteria must be observable from the agent's intent, not hidden state. Every fallback must terminate. Prefer the cheapest tool that satisfies the intent. Do not recommend tools not in the list. Use [SQUARE_BRACKET] placeholders for domain specifics.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniqueA tree of thoughts technique used to shape and strengthen the model's response.
Recommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Agentic Coding & AI Dev Tools
Autonomous Coding Agent Task Scoping Brief
Turns a vague feature request into a bounded, verifiable task brief an autonomous coding agent can execute safely.
ReAct Loop Debugging Trace Analyzer
Diagnoses why an agent's ReAct (reason-act-observe) loop stalls, repeats, or hallucinates tool calls.
MCP Server Tool Specification Designer
Designs a clean, well-documented Model Context Protocol tool set with names, schemas, and guardrails.
Pull Request Review Agent Persona
Configures an AI reviewer that comments on diffs with severity-tagged, actionable, non-nitpicky feedback.