Skip to main content
Glama

Weather forecast and alerts

weather_forecast
Read-only

Get the weather forecast for any latitude/longitude in the world, or a US street address: the next 7 days in day and night periods (temperature, rain, wind, summary). US locations use the National Weather Service and include any active watches, warnings or advisories; elsewhere the forecast is from MET Norway (in °C and km/h).

$0.002 USDC per call over x402. Failed calls cost nothing. Call without payment to get a quote.

When to use: You need the forecast for a place. Use instead: airport_delays for flight delays; geocode_address when you need coordinates for something else. Parameters: Give lat and lon (anywhere in the world) or address (US street addresses only). periods: 1-14 twelve-hour periods, default 14 (7 days). Returns: forecast[] with name, start and end, temperature, rain, wind and a summary; in the US, active NWS alerts too.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "weather_forecast"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude, e.g. 38.90 (anywhere in the world). Give lat and lon, or a US address.
lonNoLongitude, e.g. -77.04
addressNoUS street address instead of lat/lon, e.g. "1600 Pennsylvania Ave NW, Washington, DC".
paymentNoBase64 x402 payment payload. Omit it to receive a quote; sign that and call again.
periodsNoHow many 12-hour periods, 1-14 (default 14, i.e. 7 days).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / periods / description
      Added value: +"How many 12-hour periods, 1-14 (default 14, i.e. 7 days)."
  2. Changed2 schema fields changed
    • changedInput schema / properties / lat / description
      Previous value: -"Latitude, e.g. 38.98 (anywhere in the world). Give lat and lon, or a US address."New value: +"Latitude, e.g. 38.90 (anywhere in the world). Give lat and lon, or a US address."
    • changedInput schema / properties / lon / description
      Previous value: -"Longitude, e.g. -76.49"New value: +"Longitude, e.g. -77.04"
  3. Changed1 schema field changed
    • changedInput schema / properties / lat / description
      Previous value: -"Latitude, e.g. 38.98. Give lat and lon, or address."New value: +"Latitude, e.g. 38.98 (anywhere in the world). Give lat and lon, or a US address."
  4. Changed3 schema fields changed
    • addedInput schema / properties / address
      Added value: +{
      +  "description": "US street address instead of lat/lon, e.g. \"1600 Pennsylvania Ave NW, Washington, DC\".",
      +  "type": "string"
      +}
    • changedInput schema / properties / lat / description
      Previous value: -"Latitude, e.g. 38.98"New value: +"Latitude, e.g. 38.98. Give lat and lon, or address."
    • removedInput schema / required
      Removed value: -[
      -  "lat",
      -  "lon"
      -]
  5. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses cost ($0.002 USDC per call over x402), that failed calls are free, and the two-step quote flow (call without `payment` to get a quote, sign it, call again) — non-obvious operational behavior an agent cannot infer elsewhere. It also names the upstream providers and their unit conventions (°C, km/h) and flags that only US results carry NWS alerts.

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?

Front-loaded with capability and scope, then priced, then labelled When to use / Use instead / Parameters / Returns blocks. No sentence is filler, and the Returns block is necessary because there is no output schema.

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?

With no output schema, the description supplies the return shape (forecast[] with name, start/end, temperature, rain, wind, summary, plus NWS alerts in the US). Combined with pricing, provider, unit, and geographic-limit disclosures, an agent has everything needed to call it correctly on the first attempt.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description still adds the either/or rule ("Give lat and lon ... or address (US street addresses only)") and explains that the default 14 periods equals 7 days, which the schema states but does not interpret. It does not add anything further about the payment payload beyond the quote flow already covered.

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 opening sentence names a specific verb and resource ("Get the weather forecast") plus the exact scope: any lat/lon worldwide or a US street address, 7 days in 12-hour periods. It also differentiates the data sources (NWS for US with alerts, MET Norway elsewhere) and units, so the agent knows exactly what it is selecting versus airport_delays or geocode_address.

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?

There is an explicit routing block: "Use instead: airport_delays for flight delays; geocode_address when you need coordinates for something else," which genuinely disambiguates against the two most confusable siblings. The "When to use" line itself is largely a restatement of the purpose, and the 40-odd other siblings are not addressed, so it falls short of a full when/when-not treatment.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.