converse api function calling empty response

Im having issues with function calling when i request more than 1 item from a dummy api. Here is the code

tool_list = [
    {
        "toolSpec": {
            "name": "quotes",
            "description": "Fetch a random quote.",
            "inputSchema": {
                "json": {
                    "type": "object",
                    "properties": {
                        "limit": {
                            "type": "number",
                            "description": "The number of quotes we want to fetch.",
                        }
                    },
                    "required": ["limit"],
                }
            },
        }
    }
]

message_list = []

initial_message = {
    "role": "user",
    "content": [{"text": "Can you get me a random quote?"}],
}

message_list.append(initial_message)

response = bedrock.converse(
    modelId="anthropic.claude-3-sonnet-20240229-v1:0",
    messages=message_list,
    inferenceConfig={"maxTokens": 2000, "temperature": 0},
    toolConfig={"tools": tool_list},
    system=[{"text": "You can only provide quotes by using a tool."}],
)

response_message = response["output"]["message"]
print(json.dumps(response_message, indent=4))
message_list.append(response_message)

response_content_blocks = response_message["content"]

follow_up_content_blocks = []

for content_block in response_content_blocks:
    if "toolUse" in content_block:
        tool_use_block = content_block["toolUse"]
        tool_use_name = tool_use_block["name"]

        if tool_use_name == "quotes":
            url = (
                f"http://dummyjson.com/quotes/random/{tool_use_block['input']['limit']}"
            )
            tool_result_value = requests.get(url)

            follow_up_content_blocks.append(
                {
                    "toolResult": {
                        "toolUseId": tool_use_block["toolUseId"],
                        "content": [{"json": {"result": tool_result_value.json()}}],
                    }
                }
            )

if len(follow_up_content_blocks) > 0:

    follow_up_message = {
        "role": "user",
        "content": follow_up_content_blocks,
    }

    message_list.append(follow_up_message)

    response = bedrock.converse(
        modelId="anthropic.claude-3-sonnet-20240229-v1:0",
        messages=message_list,
        inferenceConfig={"maxTokens": 2000, "temperature": 0},
        toolConfig={"tools": tool_list},
        system=[{"text": "You can only provide quotes by using a tool."}],
    )
    response_message = response["output"]["message"]
    print(json.dumps(response_message, indent=4))
    message_list.append(response_message)

If i run that code this is the output and everything works.

{
    "role": "assistant",
    "content": [
        {
            "text": "Okay, let's fetch a random quote:"
        },
        {
            "toolUse": {
                "toolUseId": "tooluse_mmss3FiWTlKShgIgMafVkw",
                "name": "quotes",
                "input": {
                    "limit": 1
                }
            }
        }
    ]
}
#### Response from dummy api
[{'id': 843, 'quote': 'A Nation That Continues Year After Year To Spend More Money On Military Defense Than On Programs Of Social Uplift Is Approaching Spiritual Doom.', 'author': 'Martin Luther King  Jr.'}]
#### My complete messages
[{'role': 'user', 'content': [{'text': 'Can you get me a quote?'}]}, {'role': 'assistant', 'content': [{'text': "Okay, let's fetch a random quote:"}, {'toolUse': {'toolUseId': 'tooluse_mmss3FiWTlKShgIgMafVkw', 'name': 'quotes', 'input': {'limit': 1}}}]}, {'role': 'user', 'content': [{'toolResult': {'toolUseId': 'tooluse_mmss3FiWTlKShgIgMafVkw', 'content': [{'json': {'result': [{'id': 843, 'quote': 'A Nation That Continues Year After Year To Spend More Money On Military Defense Than On Programs Of Social Uplift Is Approaching Spiritual Doom.', 'author': 'Martin Luther King  Jr.'}]}}]}}]}]
####Final response from bedrock
{
    "role": "assistant",
    "content": [
        {
            "text": "Here is a random quote for you:\n\n\"A Nation That Continues Year After Year To Spend More Money On Military Defense Than On Programs Of Social Uplift Is Approaching Spiritual Doom.\"\n- Martin Luther King Jr."
        }
    ]
}

If i instead change my initial prompt to request more than one random quote this is my output

{
    "role": "assistant",
    "content": [
        {
            "text": "Here is how we can get 2 random quotes:"
        },
        {
            "toolUse": {
                "toolUseId": "tooluse_kuk3BxTXRgCW-WiQQriDAw",
                "name": "quotes",
                "input": {
                    "limit": 2
                }
            }
        }
    ]
}
#### Response from dummy api
[{'id': 424, 'quote': "I hated every minute of training, but I said, “Don't quit. Suffer now and live the rest of your life as a champion.”", 'author': 'Muhammad Ali'}, {'id': 1052, 'quote': 'How Hard, How Bitter It Is To Become A Man!', 'author': 'Albert Camus'}]
#### Complete list of messages
[{'role': 'user', 'content': [{'text': 'Can you get me 2 random quotes?'}]}, {'role': 'assistant', 'content': [{'text': 'Here is how we can get 2 random quotes:'}, {'toolUse': {'toolUseId': 'tooluse_kuk3BxTXRgCW-WiQQriDAw', 'name': 'quotes', 'input': {'limit': 2}}}]}, {'role': 'user', 'content': [{'toolResult': {'toolUseId': 'tooluse_kuk3BxTXRgCW-WiQQriDAw', 'content': [{'json': {'result': [{'id': 424, 'quote': "I hated every minute of 
training, but I said, “Don't quit. Suffer now and live the rest of your life as a champion.”", 'author': 'Muhammad Ali'}, {'id': 1052, 'quote': 'How Hard, How Bitter It Is To Become A Man!', 'author': 'Albert Camus'}]}}]}}]}]
#### Final response
{
    "role": "assistant",
    "content": []
}

As you can see the response come back empty. From what i gathered here acceptable format for json is the follwing:

'json': {...}|[...]|123|123.4|'string'|True|None,

And i dont see anything wrong with my input.

What am I missing here?