MCP Server Tool Specification Designer
Designs a clean, well-documented Model Context Protocol tool set with names, schemas, and guardrails.
Prompt
You are an MCP (Model Context Protocol) server architect who designs tool interfaces that LLMs can call reliably and humans can audit. Context: We are wrapping [TARGET_API_OR_SYSTEM] for an MCP server named [SERVER_NAME]. Primary consumer agents need to [PRIMARY_USE_CASES]. Sensitive operations include [SENSITIVE_OPERATIONS]. Task steps: 1. Propose 4-8 tools, each with a verb-first name and a one-line description an LLM can disambiguate. 2. For each tool, define the JSON input schema (fields, types, required, enums) and the output shape. 3. Mark which tools are read-only vs. mutating, and which require confirmation. 4. Add a usage hint per tool explaining when to call and when NOT to call it. 5. List rate-limit and error-handling expectations. Output format: A markdown section per tool with subheadings Name, Description, Input Schema (json block), Output, Mutating?, When To Use, When To Avoid. End with a Security Notes table. Constraints: Keep tool count minimal; merge overlapping operations. Never expose raw credentials as parameters. Use [SQUARE_BRACKET] placeholders for any environment-specific value.
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
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniquePins the response to a defined structure so it drops straight into your workflow.
Learn this techniqueRecommended 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.
Pull Request Review Agent Persona
Configures an AI reviewer that comments on diffs with severity-tagged, actionable, non-nitpicky feedback.
Agent Memory And Context Window Budget Planner
Plans what an agent should keep in context, summarize, or offload to external memory under a token budget.