scientific_data

Instructions

Implementation Reference

• tools/scientific_data.py:282-300 (handler)

  Main async handler function for the scientific_data tool. Dispatches to internal fetchers based on the 'dataset' parameter (earthquakes, solar_events, nasa_apod, air_quality). Returns structured JSON responses or error dicts.

  async def scientific_data_handler(arguments: dict) -> dict:
      dataset = arguments.get("dataset", "")
  
      if not dataset:
          return {"error": "dataset parameter is required"}
  
      async with aiohttp.ClientSession() as session:
          if dataset == "earthquakes":
              return await _fetch_earthquakes(session, arguments)
          elif dataset == "solar_events":
              return await _fetch_solar_events(session, arguments)
          elif dataset == "nasa_apod":
              return await _fetch_nasa_apod(session, arguments)
          elif dataset == "air_quality":
              return await _fetch_air_quality(session, arguments)
          else:
              return {"error": f"Unknown dataset: {dataset}", "available_datasets": [
                  "earthquakes", "air_quality", "solar_events", "nasa_apod"
              ]}

• tools/scientific_data.py:50-89 (schema)

  Input schema defining the tool's parameters: dataset (enum), location, latitude, longitude, radius_km, date_from, date_to, min_magnitude, max_results. The 'dataset' field is required.

  TOOL_SCHEMA = {
      "type": "object",
      "properties": {
          "dataset": {
              "type": "string",
              "enum": [
                  "earthquakes",
                  "air_quality",
                  "solar_events",
                  "nasa_apod",
                  "climate_normals",
              ],
              "description": "Scientific dataset to retrieve",
          },
          "location": {
              "type": "string",
              "description": "Location for spatially-filtered queries (city name, lat/lon, or country code)",
          },
          "latitude": {"type": "number", "description": "Latitude for geographic queries"},
          "longitude": {"type": "number", "description": "Longitude for geographic queries"},
          "radius_km": {
              "type": "number",
              "description": "Search radius in km around lat/lon (default: 500)",
              "default": 500,
          },
          "date_from": {"type": "string", "description": "Start date YYYY-MM-DD (default: 7 days ago)"},
          "date_to": {"type": "string", "description": "End date YYYY-MM-DD (default: today)"},
          "min_magnitude": {
              "type": "number",
              "description": "Minimum earthquake magnitude (for earthquakes dataset)",
              "default": 4.0,
          },
          "max_results": {
              "type": "integer",
              "description": "Maximum results to return (default: 10)",
              "default": 10,
          },
      },
      "required": ["dataset"],
  }

• tools/scientific_data.py:303-319 (registration)

  Registers the tool with the registry, providing name, description, input_schema, price_per_call_usd, stripe_price_id, handler function reference, and category.

  def register(registry) -> None:
      from server import ToolDefinition
      registry.register(ToolDefinition(
          name=TOOL_NAME,
          description=(
              "Fetch real-time scientific data from major public APIs. "
              "Datasets: earthquakes (USGS), air_quality (OpenAQ), "
              "solar_events (NASA DONKI), nasa_apod. "
              "Supports geographic filtering by lat/lon/radius. "
              "Returns structured, agent-ready data."
          ),
          input_schema=TOOL_SCHEMA,
          price_per_call_usd=TOOL_PRICE_USD,
          stripe_price_id=TOOL_STRIPE_PRICE,
          handler=scientific_data_handler,
          category="earth_science",
      ))