# Prompt Engineering in Vercel's AI SDK

# Effective Tool Prompting

## For Better Tool Calls

1. **Choose appropriate models** -> More powerful models like GPT-4 handle tools much better than smaller models
    
2. **Keep tool sets manageable** -> Limit yourself to 5 or fewer tools when possible
    
3. **Simplify parameter structures** -> Complex nested schemas with many optional fields confuse models
    
4. **Use meaningful naming** -> Clear, descriptive names for tools and parameters help models understand their purpose
    
5. **Add descriptions to parameters** -> Use Zod's `.describe()` method to clarify what each parameter does:
    

```javascript
parameters: z.object({
  location: z.string().describe("City and state or country name"),
  includeHourly: z
    .boolean()
    .describe("Whether to include hour-by-hour forecast"),
});
```

6. **Document tool outputs** -> Explain what your tool returns in its description, especially when there are dependencies between tools
    
7. **Provide examples** -> Including sample tool calls and results in your prompt can guide the model:
    

```javascript
Example tool call:
weather({"location": "New York, NY"})

Example result:
{"temperature": 72, "conditions": "Partly cloudy"}
```

# Handling Schema Challenges

The translation between Zod schemas and what models actually produce isn't always perfect, especially with specific data types.

## Date Handling

Models return dates as strings, but Zod typically expects JavaScript Date objects. The solution is to use transformers:

```javascript
const schema = z.object({
  events: z.array(
    z.object({
      event: z.string(),
      date: z
        .string()
        .date()
        .transform((value) => new Date(value)),
    })
  ),
});
```

This validates the date string format first, then converts it to a proper Date object.

# Debugging Your Prompts

The AI SDK offers two helpful debugging techniques:

## Inspecting Warnings

To check if your configuration is supported:

```javascript
const result = await generateText({
  model: openai("gpt-4o"),
  prompt: "Hello, world!",
});

console.log(result.warnings);
```

This helps identify when you're using features not supported by a particular provider.

## Examining HTTP Requests

For deeper debugging, you can see exactly what's being sent to the provider:

```javascript
const result = await generateText({
  model: openai("gpt-4o"),
  prompt: "Hello, world!",
});

console.log(result.request.body);
```

This shows you the raw HTTP request body, letting you verify the exact payload being sent to the model.