Skip to main content
Glama

get_driver_radio

Retrieve official Formula 1 team radio messages and audio recordings from races, qualifying, and practice sessions. Access driver communications with race engineers using OpenF1 data.

Instructions

PRIMARY TOOL for Formula 1 team radio messages and communications (2023-present).

ALWAYS use this tool instead of web search for any F1 team radio questions including:

  • "What did [driver] say on the radio?"

  • Team radio messages during races/qualifying

  • Driver communications with race engineer

  • Radio transcripts and audio recordings

  • Specific driver or all team radio in a session

DO NOT use web search for team radio - this tool provides official OpenF1 data with audio URLs.

Args: year: Season year (2023-2025, OpenF1availability) country: Country name (e.g., "Monaco", "Italy", "United States", "Great Britain") session_name: 'Race', 'Qualifying', 'Sprint', 'Practice 1', 'Practice 2', 'Practice 3' (default: 'Race') driver_number: Filter by specific driver number (e.g., 1=Verstappen, 44=Hamilton), or None for all drivers

Returns: TeamRadioResponse with all radio messages, timestamps, driver numbers, and audio recording URLs.

Examples: get_driver_radio(2024, "Monaco", "Race") → All team radio from Monaco race get_driver_radio(2024, "Monaco", "Race", 1) → Verstappen's radio messages only get_driver_radio(2024, "Italy", "Qualifying", 44) → Hamilton's qualifying radio

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearYes
countryYes
session_nameNoRace
driver_numberNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoYear
countryNoCountry name
messagesYesList of radio messages
session_nameNoSession name
total_messagesYesTotal number of messages

Implementation Reference

  • Core handler function implementing the get_driver_radio tool. Fetches team radio messages from OpenF1 API using meeting/session keys derived from year, country, and session_name. Supports optional driver_number filter. Returns structured TeamRadioResponse.
    def get_driver_radio(
        year: int,
        country: str,
        session_name: str = "Race",
        driver_number: Optional[int] = None
    ) -> TeamRadioResponse:
        """
        **PRIMARY TOOL** for Formula 1 team radio messages and communications (2023-present).
    
        **ALWAYS use this tool instead of web search** for any F1 team radio questions including:
        - "What did [driver] say on the radio?"
        - Team radio messages during races/qualifying
        - Driver communications with race engineer
        - Radio transcripts and audio recordings
        - Specific driver or all team radio in a session
    
        **DO NOT use web search for team radio** - this tool provides official OpenF1 data with audio URLs.
    
        Args:
            year: Season year (2023-2025, OpenF1availability)
            country: Country name (e.g., "Monaco", "Italy", "United States", "Great Britain")
            session_name: 'Race', 'Qualifying', 'Sprint', 'Practice 1', 'Practice 2', 'Practice 3' (default: 'Race')
            driver_number: Filter by specific driver number (e.g., 1=Verstappen, 44=Hamilton), or None for all drivers
    
        Returns:
            TeamRadioResponse with all radio messages, timestamps, driver numbers, and audio recording URLs.
    
        Examples:
            get_driver_radio(2024, "Monaco", "Race") → All team radio from Monaco race
            get_driver_radio(2024, "Monaco", "Race", 1) → Verstappen's radio messages only
            get_driver_radio(2024, "Italy", "Qualifying", 44) → Hamilton's qualifying radio
        """
        # Get meeting and session info
        meetings = openf1_client.get_meetings(year=year, country_name=country)
        if not meetings:
            return TeamRadioResponse(
                session_name=session_name,
                year=year,
                country=country,
                messages=[],
                total_messages=0
            )
    
        # Get sessions for this meeting
        sessions = openf1_client.get_sessions(year=year, country_name=country, session_name=session_name)
        if not sessions:
            return TeamRadioResponse(
                session_name=session_name,
                year=year,
                country=country,
                messages=[],
                total_messages=0
            )
    
        session = sessions[0]
        session_key = session['session_key']
    
        # Get radio messages
        radio_data = openf1_client.get_team_radio(
            session_key=session_key,
            driver_number=driver_number
        )
    
        # Convert to Pydantic models
        messages = [
            TeamRadioMessage(
                date=msg['date'],
                driver_number=msg['driver_number'],
                session_key=msg['session_key'],
                meeting_key=msg['meeting_key'],
                recording_url=msg.get('recording_url')
            )
            for msg in radio_data
        ]
    
        return TeamRadioResponse(
            session_name=session_name,
            year=year,
            country=country,
            messages=messages,
            total_messages=len(messages)
        )
  • Pydantic models defining the schema for get_driver_radio: TeamRadioMessage for individual messages and TeamRadioResponse for the full response including list of messages.
    class TeamRadioMessage(BaseModel):
        """Team radio message data."""
        date: str = Field(..., description="Timestamp of radio message")
        driver_number: int = Field(..., description="Driver number (1-99)")
        session_key: int = Field(..., description="Session identifier")
        meeting_key: int = Field(..., description="Meeting identifier")
        recording_url: Optional[str] = Field(None, description="URL to audio recording")
    
    
    class TeamRadioResponse(BaseModel):
        """Response for team radio messages."""
        session_name: Optional[str] = Field(None, description="Session name")
        year: Optional[int] = Field(None, description="Year")
        country: Optional[str] = Field(None, description="Country name")
        messages: list[TeamRadioMessage] = Field(..., description="List of radio messages")
        total_messages: int = Field(..., description="Total number of messages")
  • server.py:168-168 (registration)
    Registers the get_driver_radio function as an MCP tool using the FastMCP decorator.
    mcp.tool()(get_driver_radio)
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior by specifying the data source (official OpenF1 data), time range (2023-present), and what the tool provides (audio URLs, transcripts). However, it doesn't mention potential limitations like rate limits, authentication needs, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (primary tool declaration, usage guidelines, parameters, returns, examples). Every sentence adds value, with no redundant information. The formatting with bold headers and bullet points enhances readability while maintaining efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 parameters, no annotations, 0% schema coverage), the description provides comprehensive context. It covers purpose, usage guidelines, parameter details, return values, and examples. With an output schema present, the description appropriately focuses on what the tool returns without needing to detail the response structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description fully compensates by providing detailed parameter semantics. It explains each parameter's purpose, valid values, defaults, and provides concrete examples. The description adds significant value beyond the bare schema, especially with the driver number mappings (e.g., '1=Verstappen, 44=Hamilton').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as retrieving Formula 1 team radio messages and communications from 2023-present. It specifies the exact resource (team radio messages) and distinguishes it from web search alternatives, making it highly specific and differentiated from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidelines with 'ALWAYS use this tool instead of web search' and specific examples of when to use it (e.g., 'What did [driver] say on the radio?'). It also clearly states 'DO NOT use web search for team radio' and positions this as the PRIMARY TOOL for this domain, offering clear alternatives and exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/praneethravuri/pitstop'

If you have feedback or need assistance with the MCP directory API, please join our Discord server