Get statistically rigorous weather and climate context for any location on Earth (land only). Answers natural-language questions with 10-day forecast data and historical percentile rankings against a 35-year ERA5 daily climatology (1991-2025, WMO 1991-2020 normals). Use this when you need to know not just what conditions are or will be, but how unusual they are relative to history.

query MUST be phrased as a question in one of these forms (the location goes where LOCATION is shown; the underlying parser matches these patterns specifically and will fail on other phrasings, e.g. "weather context for LOCATION" does not work):

• "Will LOCATION be warmer/wetter than normal this week?"

• "Has LOCATION been dry this water year?" / "this year?"

• "How cold/warm/wet was last winter/spring/summer/fall in LOCATION?"

• "What is the wettest/driest month in LOCATION?"

Get 10-day forecast and 35-year historical climate context for exact coordinates. Use when you have a specific latitude/longitude (a property, field, trailhead, or site) rather than a place name — this skips geocoding entirely. Land locations only.

Get water year precipitation and temperature status for a location: totals since the start of the water/calendar year (Oct 1 for North America, Jan 1 elsewhere), percentile rank against the same period across 35 historical years, and whether conditions are notably wet, dry, warm, or cold. Built for drought monitoring, water resource, agricultural, and fire-planning contexts. location can be a place name ("Casper WY") or "lat,lon" coordinates.

Compare current or forecast conditions at a location to 35-year historical normals. Returns percentile rankings, not vague comparisons. Use for questions like "is this week unusually warm" or "will it be wetter than normal this month". variable must be "temperature" or "precipitation". time_window is optional free text (e.g. "this week", "this month") — defaults to "this week".

Compare precipitation, temperature, or snowfall across 2-10 locations in a single ranked comparison, computed directly by Baseline. Use this instead of calling get_climate_context or get_water_year_status once per location and comparing the answers yourself — the ranking and percent-of-normal figures in the result come from Baseline, not from your own arithmetic over several separate answers.

Provide EITHER locations (a list of 2-10 place names and/or "lat,lon" strings) OR category (a curated group name) — not both.

Valid category values: colorado_ski_resorts, wyoming_ski_resorts, utah_ski_resorts, wyoming_watersheds, colorado_river_basin_states, great_plains_ag, major_us_cities, major_european_cities, us_national_parks.

variable: "precipitation" (default), "temperature", or "snowfall". Snowfall is sourced from a different, coarser (0.25-degree) Open-Meteo archive than precipitation/temperature (0.1-degree ERA5-Land) — results are correct but not directly resolution-comparable across variables.

period: "water_year" (default, Oct 1 / Jan 1 to date), "season" (also set season="winter"/"spring"/"summer"/"fall" and optionally year), "month" (also set month=1-12 and optionally year), or "ski_season" (fixed Nov 1 - Apr 30 window; optionally set year=<November's year>, e.g. year=2019 for the 2019-2020 season; defaults to the most recently started ski season). Custom date ranges are not supported — use "water_year", "season", "month", or "ski_season".