# Designing Tools That Agents Use Well — LangGraph Agents & Multi-Agent Systems

Source: https://www.geekswithgeeks.com/en/langgraph-agents/a-tooldesign

> Write tools with clear names, narrow scope and safe behaviour.

## Tools are an interface for a model

The model chooses tools from their **names, descriptions and argument schemas**, so these are your prompt. Good tools are **narrow** (one clear job), **well named** (`get_order_status`, not `do_stuff`), **documented** (when to use, what each argument means, an example), return **concise, structured results** (not megabytes of text), and give **actionable error messages** the model can recover from ("order_id must be 6 digits"). Prefer a few good tools over many overlapping ones. Validate all arguments in code, enforce permissions per user, make write actions **idempotent** where possible, and never let a tool run arbitrary code or SQL built from model output without strict checks.

## Weak versus strong tool definitions

The second version tells the model when to use the tool and how to recover from errors. Illustrative; not run here.

```python
# weak
@tool
def lookup(x): 
    """Look something up."""
    ...

# strong
@tool
def get_order_status(order_id: str) -> dict:
    """Return the status of ONE customer order.
    Use when the user asks where an order is. order_id is exactly 6 digits, e.g. "481516".
    Returns {"status": "...", "eta": "..."} or {"error": "..."}."""
    if not (order_id.isdigit() and len(order_id) == 6):
        return {"error": "order_id must be exactly 6 digits"}   # recoverable message
    ...
```

## Return errors as data

A clear error message in the tool result lets the model correct itself on the next step instead of crashing the run.

**Quiz:** Which tool design is better for an agent?

- [ ] One huge tool that does everything
- [x] One narrow, well-named tool with a clear description and recoverable errors
- [ ] Tools with no descriptions
- [ ] Tools that return raw database dumps

*Answer:* One narrow, well-named tool with a clear description and recoverable errors. The model relies on names, descriptions and error messages to use tools well.