Skip to main content
Glama

Get weather forecast at coordinates

get_point_forecast

Fetch weather, marine, or air-quality forecasts for any lat/lon point. Includes decoded wind direction, precipitation type, and weather codes with variable parameter guide.

Instructions

Fetch machine-readable weather, marine, or air-quality forecast data for a lat/lon point from the Windy Point Forecast API (https://api.windy.com/point-forecast). Requires WINDY_API_KEY. Returns shaped timesteps with decoded wind direction, precipitation type, and WMO weather codes plus a parameterGuide explaining each requested variable. Pick a regional model when available (iconEu for Europe, hrrrConus for US, arome for France). Use list_forecast_options to browse all models, parameters, and pressure levels.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
latYesLatitude in WGS84 decimal degrees (-90 to 90). Rounded to 2 decimals by the API (~1 km).
lonYesLongitude in WGS84 decimal degrees (-180 to 180). Rounded to 2 decimals by the API (~1 km).
modelNoNumerical weather/sea/air-quality model. Pick a regional model when available for better terrain resolution. Weather models: gfs (global default), icon, iconD2 (DE/AT/CH), iconEu, arome*, nam*, hrrr*, canHrdps. Sea: gfsWave, iconWave, iconEuWave, canRdwpsWave, cmems. Air quality: cams (global), camsEu (Europe + pollen). Details: gfs: Global (NOAA GFS, ~13 km). Default worldwide fallback. — Any location globally when no regional high-res model applies. Good baseline for multi-day trail planning. | icon: Global (DWD ICON-Global). — Global coverage with a European model; alternative to GFS worldwide. | iconD2: Germany, Austria, Switzerland — high resolution (~2 km). — Alpine trails in DE/AT/CH where terrain detail matters. | iconEu: Europe and surrounding areas (~7 km). — European hiking/cycling; better than GFS for the Alps, Pyrenees, etc. | arome: France and surrounding areas (Météo-France AROME). — French trails including Alps, Massif Central, Pyrenees fringes. | aromeAntilles: French Antilles (Caribbean). — Guadeloupe, Martinique, and nearby islands. | aromeFrance: Metropolitan France only. — Mainland France trails when you want the France-specific AROME run. | aromeReunion: Réunion island (Indian Ocean). — Piton des Neiges, cirques, and Réunion hiking. | namConus: Continental USA and surrounding areas (NAM). — US lower-48 trail forecasts (Appalachian, Rockies, etc.). | namHawaii: Hawaii. — Hawaiian island trails and volcanoes. | namAlaska: Alaska and surrounding areas. — Alaskan wilderness and mountain routes. | hrrrConus: Continental USA — high resolution (~3 km, short-range). — Same-day / next-day US trail weather where convection and terrain matter. | hrrrAlaska: Alaska — high resolution short-range. — Detailed short-range forecasts for Alaskan trails. | canHrdps: Canada — high resolution (HRDPS). — Canadian Rockies, Coast Mountains, and other CA trail areas. | gfsWave: Global ocean waves (excludes Hudson Bay partly, Black Sea, Caspian, most Arctic). — Coastal hikes, beach trails, kayak/ferry crossings on open ocean. | iconWave: Global wave model (DWD ICON-GWAM). — Global marine conditions; alternative wave model to gfsWave. | iconEuWave: European seas (ICON-EWAM). — Mediterranean, Atlantic fringe, North Sea coastal trails. | canRdwpsWave: Canadian waters. — Pacific/Atlantic/Arctic coastal routes in Canada. | cmems: Global ocean currents (Copernicus Marine Service). — Coastal current safety for swimming, paddling, or tidal flat crossings. | cams: Global air quality (Copernicus CAMS). — Smoke, dust, or pollution affecting trail air quality worldwide. | camsEu: Europe — includes pollen (CAMS regional). — European trails during hay-fever season or smog events.gfs
parametersNoOne or more forecast parameters. Default bundle covers typical trail planning: temp, wind, windGust, precip, rh, pressure, ptype, lclouds.
levelsNoPressure/geopotential levels for level-aware params (temp, dewpoint, wind, rh, gh). Other params always use surface. Default ['surface']. Levels: surface: Surface level (default). Best for trailhead conditions: ground temperature, surface wind, and precipitation at the coordinate. | 1000h: 1000 hPa (~sea level). Useful for coastal/lowland forecasts when surface orography differs from the model grid cell. | 950h: 950 hPa (~500 m). Lower foothills and valley inversions. | 925h: 925 hPa (~800 m). Mid-elevation valleys and lower mountain slopes. | 900h: 900 hPa (~1 km). Lower mountain ridges and high valleys. | 850h: 850 hPa (~1.5 km). Standard level for free-atmosphere temperature/wind; often used for mountain-pass and sub-alpine conditions. | 800h: 800 hPa (~2 km). High ridges and lower alpine terrain. | 700h: 700 hPa (~3 km). High alpine / treeline elevation band. | 600h: 600 hPa (~4.2 km). Upper alpine and lower glaciated terrain. | 500h: 500 hPa (~5.6 km). High peaks and upper-atmosphere weather systems. | 400h: 400 hPa (~7.2 km). Very high summits; jet-stream proximity. | 300h: 300 hPa (~9.1 km). Jet-stream level; strong winds aloft. | 200h: 200 hPa (~11.8 km). Upper troposphere. | 150h: 150 hPa (~13.5 km). Near tropopause.
max_stepsNoOptional cap on returned forecast timesteps (from the start). Omit for the full model run. Use to keep responses small (e.g. 24 for ~3 days of 3-hourly data).
Behavior4/5

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

No annotations are provided, so the description bears the full burden. It explains that the tool 'Returns shaped timesteps with decoded wind direction, precipitation type, and WMO weather codes plus a parameterGuide' and mentions lat/lon rounding. It could be more transparent about error handling or rate limits, but overall it provides good insight into behavior.

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

Conciseness4/5

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

The description is concise (two sentences plus a recommendation) and front-loaded with purpose and authentication. It could be more structured, but it avoids unnecessary verbosity and is efficient.

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

Completeness4/5

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

Given the tool's complexity and no output schema, the description covers core purpose, authentication, model choice guidance, and return format. It lacks details on pagination or large response handling, but overall it is fairly complete for an agent to use effectively.

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

Parameters3/5

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

Schema has 100% coverage, so baseline is 3. The description adds little beyond the schema for parameters, as the schema already contains extremely detailed descriptions for model and parameters. However, the tool description does list a default parameter set, providing some added value.

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 title and description clearly specify 'Fetch machine-readable weather, marine, or air-quality forecast data for a lat/lon point from the Windy Point Forecast API.' The verb 'Fetch' and resource 'forecast data' are specific, and it distinguishes from siblings like list_forecast_options (which browses options) and route-related tools.

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

Usage Guidelines4/5

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

The description states the requirement for WINDY_API_KEY and advises to 'Pick a regional model when available' while referencing list_forecast_options to browse all models. It does not explicitly state when not to use it, but the context is clear.

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/chiraggahujaa/trails-mcp'

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