add prompting tips

Author: kentcdodds

exercises/05.prompts/README.mdx

@@ -91,4 +91,17 @@ This exercise will introduce you to MCP's prompt capabilities, showing how to
 declare prompt support, register prompts with arguments, and return structured
 messages for downstream use.
 
+## Prompting Tips
+
+When designing prompts for your MCP server, consider these best practices:
+
+- **Be specific and clear**: Use precise language and provide concrete examples when possible
+- **Structure your prompts**: Break complex tasks into clear steps or sections
+- **Include context**: Provide relevant background information that helps the model understand the task
+- **Use consistent formatting**: Maintain a consistent style across your prompts for better user experience
+- **Test and iterate**: Experiment with different prompt formulations to find what works best
+- **Consider edge cases**: Think about how your prompts might fail and provide fallback instructions
+
+For a comprehensive survey of prompt engineering techniques and best practices, see [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](https://arxiv.org/abs/2406.06608) by Schulhoff et al., which provides detailed analysis of 58 LLM prompting techniques and guidelines for working with state-of-the-art language models.
+
 - 📜 [MCP Prompts Specification](https://modelcontextprotocol.io/specification/2025-06-18/server/prompts)