open-data-mcp

dataandbeyond--weather-forecast

Read-only

Fetch MET Norway weather forecasts for any location by place name or coordinates, with daily or hourly output up to 10 days. Geocoding included for accurate local results.

Instructions

MET Norway forecasts for a place name or coordinates, hourly or daily, up to 10 days. Calls api.met.no (and Nominatim for geocoding) directly.

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": "dataandbeyond--weather-forecast"
  }
}

Input Schema

Name	Required	Description	Default
`days`	No	Days Example values: 3
`output`	No	Output Example values: "daily"	daily
`waitSecs`	No	Max seconds (0–45, default 30) to cap the wait for the Actor run to reach terminal state. For long-running Actors the response returns at the cap with the current run status; follow `nextStep` to poll via get-actor-run. Set to 0 to fire-and-forget.
`locations`	No	Place names like "Copenhagen" or "Paris, US" (geocoded with OpenStreetMap Nominatim), or coordinates like "55.676,12.568". Example values: ["Aarhus","Paris, US","55.676,12.568"]

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Oct 30, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that by naming the upstream services (api.met.no and Nominatim geocoding), which warns of external latency and third-party dependency. However, it omits the async Actor-run semantics that the `waitSecs` parameter implies (returns at the cap with a run status, poll via nextStep), which materially affects how an agent should call it.

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?

Two short sentences, front-loaded with what the tool produces, followed by the dependency note. Nothing is padded and no sentence is redundant.

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

Completeness3/5

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

Four all-optional parameters keep the tool simple, but with no output schema the description should say something about the shape of a forecast response and about multi-location behavior (a list is accepted with a default of two locations). It also skips the async wait/poll behavior that `waitSecs` governs, leaving an agent to discover both by calling.

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 description coverage is 100%, so the baseline is 3; the description exceeds it by adding the "up to 10 days" cap, which is not stated anywhere in the schema and bounds the `days` parameter. It otherwise restates what the schema already spells out (place name vs lat,lon, hourly/daily), but the horizon limit is real added meaning.

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

Purpose4/5

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

Names a specific verb and resource ("MET Norway forecasts") plus the accepted inputs (place name or coordinates) and output modes (hourly or daily), so an agent immediately knows what it returns. It doesn't need to differentiate against siblings, which cover unrelated domains (company registries, PubMed, VIN), so nothing is lost there.

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

Usage Guidelines3/5

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

The description implies the use case (get a forecast for one or more locations, hourly or daily) but never states when to prefer hourly vs daily, when to pick coordinates over place names, or the 10-day ceiling implied as a constraint on the `days` parameter. No exclusions or alternatives are given because there are no close siblings, but the selection logic between its own modes is left implicit.

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

Deploy Server