Skip to main content
Glama

Jma Station Search

jma_station_search
Read-onlyIdempotent

Find Japan Meteorological Agency (JMA) observation stations (staffed weather stations and AMeDAS automatic stations) by name and/or prefecture. Returns station_id (the handle jma_past_daily and jma_climate_normals take), Japanese name, kana, romaji, coordinates, elevation, which elements the station observes (precipitation, temperature, wind, sunshine, humidity, snow) and whether it has closed. Name accepts romaji ("Nozawa Onsen"), katakana or kanji. Pass prefecture (English or Japanese name, or 2-digit JMA area number; Hokkaido is 14 sub-areas) to be fast; without it every area is scanned. Sourced from the Japan Meteorological Agency, past weather data search.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "Nozawa Onsen",
      "prefecture": "Nagano"
    },
    "name": "jma_station_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax stations to return (default 25, max 100).
queryNoStation name, e.g. "Nozawa Onsen", "野沢温泉", "Naha".
observesNoOnly stations observing this element: precipitation, temperature, wind, sunshine, humidity or snow.
prefectureNoPrefecture or Hokkaido sub-area, e.g. "Nagano", "長野県", "48".

Output Schema

NameRequiredDescriptionDefault
countNo
foundNofalse when nothing matched; see reason
notesNoInterpretation notes
reasonNoWhy nothing was returned
sourceNoPublisher and dataset
stationsNo
candidatesNo
data_as_ofNoDate the data is current to (ISO)
total_matchesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds value beyond that by disclosing the full result shape (id, name, kana, romaji, coordinates, elevation, observed elements, closed flag) and the cost behavior of omitting prefecture. It does not mention pagination beyond limit or any rate/authorization considerations, which keeps it out of the top band.

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?

Effectively a single front-loaded paragraph: purpose and output identity first, then input formats, then the performance caveat. Dense but every clause earns its place; the enumeration of returned fields is the longest block but supports selection by observation element.

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?

Output schema exists, so the detailed return-field list is partly redundant, but it usefully signals that closed stations and observation elements are filterable/visible. Combined with annotations and full schema coverage, an agent has what it needs to call this correctly. Minor gap: no guidance on result ordering or what an empty result means.

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 coverage is 100%, so the baseline is 3. The description does add some meaning beyond the schema — name accepts romaji, katakana or kanji, and prefecture accepts English, Japanese or a 2-digit JMA area number with Hokkaido split into 14 sub-areas — but it says nothing about limit semantics or how query and prefecture combine when both are supplied. Given the schema already carries all four descriptions and examples, the extra semantics are real but partial.

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?

Specific verb plus resource: "Find Japan Meteorological Agency (JMA) observation stations (staffed weather stations and AMeDAS automatic stations) by name and/or prefecture." It also states the downstream role of the output ("station_id (the handle jma_past_daily and jma_climate_normals take)"), which distinguishes it from the two data-retrieval siblings.

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?

Gives clear operational context: use it to resolve a station before calling jma_past_daily or jma_climate_normals, and "Pass prefecture ... to be fast; without it every area is scanned." That is a real performance-based usage rule. It stops short of explicit exclusions or naming other lookup routes (e.g. a sibling area resolver) for the prefecture/area-code input.

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.