Use OllamaFunctions to build AgentExecutor but return errors with tools

[DiaQusNet]

Checked other resources

• [X] I added a very descriptive title to this issue.
• [X] I searched the LangChain documentation with the integrated search.
• [X] I used the GitHub search to find a similar question and didn't find it.
• [ ] I am sure that this is a bug in LangChain rather than my code.
• [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain_experimental.llms.ollama_functions import OllamaFunctions
from langchain_core.tools import tool
from langchain_community.tools.tavily_search import TavilySearchResults
import os
from langchain.agents import AgentExecutor
from langchain.agents import create_tool_calling_agent
from langchain import hub

os.environ["TAVILY_API_KEY"] = ''

llm = OllamaFunctions(model="llama3:8b", temperature=0.6, format="json")

@tool
def multiply(first_int: int, second_int: int) -> int:
    """Multiply two integers together."""
    return first_int * second_int

@tool
def search_in_web(query: str) -> str:
    """Use Tavily to search information in Internet."""
    search = TavilySearchResults(max_results=2)
    context = search.invoke(query)
    result = ""
    for i in context:
        result += f"In site:{i['url']}, context shows:{i['content']}.\n"
    return result

tools=[
        {
            "name": "multiply",
            "description": "Multiply two integers together.",
            "parameters": {
                "type": "object",
                "properties": {
                    "first_int": {
                        "type": "integer",
                        "description": "The first integer number to be multiplied. " "e.g. 4",
                    },
                    "second_int": {
                        "type": "integer",
                        "description": "The second integer to be multiplied. " "e.g. 7",
                    },
                },
                "required": ["first_int", "second_int"],
            },
        },
        {
            "name": "search_in_web",
            "description": "Use Tavily to search information in Internet.",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {
                        "type": "str",
                        "description": "The query used to search in Internet. " "e.g. what is the weather in San Francisco?",
                    },
                },
                "required": ["query"],
            },
        }]

prompt = hub.pull("hwchase17/openai-functions-agent")

agent = create_tool_calling_agent(llm, tools, prompt)

agent_executor = AgentExecutor(agent=agent, tools=tools)


### Error Message and Stack Trace (if applicable)

---------------------------------------------------------------------------
Traceback (most recent call last):
  File "/media/user/My Book/LLM/Agent/check.py", line 80, in <module>
    agent_executor = AgentExecutor(agent=agent, tools=tools)
  File "/home/user/anaconda3/envs/XIE/lib/python3.9/site-packages/pydantic/v1/main.py", line 339, in __init__
    values, fields_set, validation_error = validate_model(__pydantic_self__.__class__, data)
  File "/home/user/anaconda3/envs/XIE/lib/python3.9/site-packages/pydantic/v1/main.py", line 1100, in validate_model
    values = validator(cls_, values)
  File "/home/user/anaconda3/envs/XIE/lib/python3.9/site-packages/langchain/agents/agent.py", line 981, in validate_tools
    tools = values["tools"]
KeyError: 'tools'

### Description

I am tring to initialize AgentExecutor with OllamaFunctions.
I have check the `OllamaFunctions.bind_tools` and it works well. 
So I want to use AgentExecutor to let llm to response.
But `keyerror: tools ` confused me, since the `create_tool_calling_agent` use the same `tools` value.
Does anyone know how to fix this problem?

### System Info

langchain==0.2.1
langchain-community==0.0.38
langchain-core==0.2.1
langchain-experimental==0.0.58
langchain-openai==0.1.7
langchain-text-splitters==0.2.0
langchainhub==0.1.16
platform: Ubuntu 20.04
python==3.9