Gachi Data API — Japan Station & Accessibility Data

get_station_alerts

Read-onlyIdempotent

Live JMA river flood forecasts and landslide alerts affecting a station's prefecture — NOT general weather warnings. Ask by station name in Japanese (新宿) or romaji (Shinjuku). Prefecture-level match (station master is Greater Tokyo). Relay of official JMA facts.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`station_name`	Yes	Station name in Japanese (新宿) or romaji (Shinjuku).

Output Schema

TableJSON Schema

Name	Required	Description
`count`	No	Number of alerts.
`stale`	No	True if stale.
`alerts`	No	JMA alerts affecting the prefecture.
`station`	No	Resolved station.
`disclaimer`	No	Relay disclaimer.
`fetched_at`	No	When the snapshot was fetched.
`attribution`	No	Data source(s), license and provenance — an object, or an array of sources.

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedJul 12, 2026
- addedOutput schema / properties / alerts / description
```
Added value: +"JMA alerts affecting the prefecture."
```
- changedOutput schema / properties / attribution / description
```
Previous value: -"Data source, license and provenance."New value: +"Data source(s), license and provenance — an object, or an array of sources."
```
- removedOutput schema / properties / attribution / type
```
Removed value: -"object"
```
- addedOutput schema / properties / count / description
```
Added value: +"Number of alerts."
```
- removedOutput schema / properties / count / type
```
Removed value: -"integer"
```
- addedOutput schema / properties / disclaimer / description
```
Added value: +"Relay disclaimer."
```
- removedOutput schema / properties / disclaimer / type
```
Removed value: -"string"
```
- addedOutput schema / properties / fetched_at / description
```
Added value: +"When the snapshot was fetched."
```
- removedOutput schema / properties / fetched_at / type
```
Removed value: -"string"
```
- addedOutput schema / properties / stale / description
```
Added value: +"True if stale."
```
- removedOutput schema / properties / stale / type
```
Removed value: -"boolean"
```
- addedOutput schema / properties / station / description
```
Added value: +"Resolved station."
```
- removedOutput schema / properties / station / type
```
Removed value: -"object"
```

Changed1 schema field changedJul 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Live JMA alerts for a station's prefecture.",
+  "properties": {
+    "alerts": {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "attribution": {
+      "description": "Data source, license and provenance.",
+      "type": "object"
+    },
+    "count": {
+      "type": "integer"
+    },
+    "disclaimer": {
+      "type": "string"
+    },
+    "fetched_at": {
+      "type": "string"
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "station": {
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

First observedJul 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds valuable context beyond this: the prefecture-level matching (station master is Greater Tokyo), the fact that it's a 'Relay of official JMA facts' (not original analysis), and that it excludes general warnings. These traits meaningfully shape agent expectations.

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?

Three sentences, each earning its place: what it is, how to query, and scope/caveat. The dash for exclusion is efficient. No padding.

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?

For a one-parameter tool with an output schema, the description covers content type, query language, matching scope, and source. It gives the agent enough to decide when to use it and what to expect, without needing to inspect the output schema.

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%, and the description reinforces the Japanese/romaji format. It also adds the nuance that the station_name is used for a prefecture-level match, which is extra meaning beyond the schema's simple 'station name' definition. This justifies a score above the baseline 3.

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 description clearly states the tool provides 'Live JMA river flood forecasts and landslide alerts affecting a station's prefecture' and explicitly excludes 'general weather warnings', distinguishing it from likely siblings like get_active_alerts. The verb 'Live' and resource 'JMA alerts' are specific and unambiguous.

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?

It gives clear usage context: ask by station name in Japanese or romaji, and notes the prefecture-level match. It explicitly says 'NOT general weather warnings', which provides a when-not scenario. However, it does not name alternative tools directly, so it falls short of full 5.

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

All Gachi Data API — Japan Station & Accessibility Data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.