Write Tool Descriptions a Model Will Actually Use Correctly
Rewrite ambiguous tool/function definitions so an agent reliably selects the right tool with the right arguments.
Reduce wrong-tool and bad-argument errors by making each tool's name, description, and parameter docs unambiguous to the model.
At a glance
Access
Free prompt
Open to copy — no account or payment needed.
Prompt objective
Reduce wrong-tool and bad-argument errors by making each tool's name, description, and parameter docs unambiguous to the model.
Real use case
An agent keeps calling search_users when it should call get_user_by_id, because the two tool descriptions overlap and the parameter docs are vague.
Customize these fields first
Replace the placeholders with your own context before you run the prompt. That usually improves the first output more than adding more instructions later.
Prompt
You are an expert in writing tool/function definitions for LLM agents (OpenAI tools, Anthropic tool use, MCP). Improve the tool set below so the model selects and calls each tool correctly. Current tools (name + current description + parameters): [PASTE CURRENT TOOL DEFINITIONS] Observed mistakes: [WHICH TOOLS GET CONFUSED OR MIS-CALLED] For each tool, return: 1. A revised name (verb-based, no overlap with siblings). 2. A revised description that states exactly when to use it AND when NOT to use it (contrast with the most-confused sibling tool). 3. Parameter docs: for each argument, type, whether required, allowed values/format, and a concrete example. 4. A one-line note on side effects (read-only vs mutating) so the model treats writes carefully. Then add a short "tool selection guide" the system prompt can include, mapping common user intents to the right tool. Output as a clean tool spec ready to drop into the agent config.
Open directly in an AI — the text is pre-filled:
How to use this prompt
- 1Replace the key placeholders first: PASTE CURRENT TOOL DEFINITIONS, WHICH TOOLS GET CONFUSED OR MIS-CALLED.
- 2Replace any bracketed placeholders like [this] with your own context.
- 3Add extra background information when you want more tailored results.
- 4Combine multiple prompts in one conversation when you need a richer output.
- 5Save your best-performing prompts so they are easy to reuse later.
Next best step
Open the guide first, then branch only if you still need more.
A guide for technical builders choosing between prompts, coding workflows, and agent-based implementation.
If this prompt is close but not quite right, generate variants next. If the job is recurring, move into the course library after the guide.
Related prompts
View allDesign an MCP Server to Expose Internal Tools to an Agent
Plan a Model Context Protocol server that safely exposes your internal data and actions as tools an agent can call.
Best for
Get a concrete MCP server design — tools, resources, auth, and limits — so agents in Claude, Claude Code, or other MCP clients can use your systems.
Build a Retrieval (RAG) Tool an Agent Can Query
Design a retrieval tool that returns grounded, citable chunks so an agent answers from your data instead of guessing.
Best for
Give an agent a clean retrieval interface — query in, ranked passages with sources out — that minimizes hallucination.
Explore other prompt categories
Move sideways into adjacent libraries when the current category is not the full answer.
Every prompt here is free. The course teaches the thinking behind them.
Copy as many prompts as you like. When you want to move from single prompts to a repeatable AI workflow, Learn AI in 30 Days walks through it, one day at a time.
Buy the course once ($15/$20 by length), or go all-access for $10/mo with a verifiable certificate.