How should you write tool descriptions for reliable agent tool selection?
mediumAnswer
- (1) Descriptive tool name: not
f1. - (2) Rich description: what the tool does, when to use it, what to NOT use it for.
- (3) Full argument schema with descriptions per field.
- (4) Example calls in the description when the signature is subtle.
- (5) Constraints: 'this tool is idempotent', 'costs $0.05 per call'.
- (6) Fewer tools > many tools: 5-10 well-scoped is better than 30 overlapping ones.
- Prompt-engineering the tool description is often more impactful than fine-tuning.
Check yourself โ multiple choice
- Vague short names
- Descriptive names + rich when-to-use description + argument schema + examples + constraints; keep tool set small and non-overlapping
- Random naming
- Same for all tools
Tool descriptions: names / when-to-use / schema / examples / constraints; small non-overlapping set.
#agents#tools#prompting
Practise LLMs & GenAI
214 interview questions in this topic.
Related questions
- How does function calling / tool use work in modern LLMs?
- What is prompt chaining and why prefer it over one big prompt?
- Describe a basic ReAct / agent loop.
- How do you scale to hundreds of tools without overwhelming the LLM?
- Do agents plan explicitly or should we let them just react?
- How does a coding agent (SWE-agent, Aider, Cursor) actually work?