Initialize Claude Agent with Custom Tools

Start by setting up your development environment for the Claude Agents SDK. Define a `Tool` for fetching simulated crypto transaction data (`get_transaction_details(tx_id: str)`) and another for fetching relevant news articles (`search_crypto_news(query: str)`). Implement basic Python functions that return dummy data for these tools. Then, initialize a Claude agent with these tools, instructing it to monitor for large, suspicious transactions followed by news of scams. Include Python code snippets.

```python
from anthropic import Anthropic
from anthropic.agents import Tool, Agent
import json
import time

# Initialize Anthropic client
client = Anthropic(api_key="YOUR_ANTHROPIC_API_KEY")

# Define a dummy tool for fetching transaction data
def get_transaction_details(tx_id: str) -> str:
    """Fetches details for a given crypto transaction ID."""
    # Simulate fetching data
    if tx_id == "tx3":
        return json.dumps({
            "tx_id": tx_id, "from_addr": "C", "to_addr": "Monero_Mixer", 
            "amount": "1200XMR", "currency": "XMR", "timestamp": "T3"
        })
    return json.dumps({"tx_id": tx_id, "status": "not_found"})

# Define a dummy tool for searching crypto news
def search_crypto_news(query: str) -> str:
    """Searches for crypto news articles related to the query."""
    # Simulate news search
    if "scam" in query.lower() and "whale" in query.lower():
        return json.dumps([{"headline": "Whale loses millions in hardware wallet scam", "content": "A prominent crypto whale reported losing over $282M in BTC and LTC...", "timestamp": "T2.5"}])
    return json.dumps([])

# Create Tool instances
transaction_tool = Tool(name="get_transaction_details", description=get_transaction_details.__doc__, input_schema={"$schema": "http://json-schema.org/draft-07/schema#", "type": "object", "properties": {"tx_id": {"type": "string"}}, "required": ["tx_id"]})
news_tool = Tool(name="search_crypto_news", description=search_crypto_news.__doc__, input_schema={"$schema": "http://json-schema.org/draft-07/schema#", "type": "object", "properties": {"query": {"type": "string"}}, "required": ["query"]})

# Initialize the agent. Your task is to define the agent's prompt and make it use these tools.
# agent = Agent(client=client, tools=[transaction_tool, news_tool], ...)
# response = agent.run("Monitor for suspicious crypto activities and alert on potential scams.")
```