Japan Agent API

Japan typhoon bulletins (JMA)

jp_typhoons

Read-only

Which typhoons is JMA issuing bulletins for right now, and what do the bulletins forecast? Number, name, center position, central pressure, maximum wind, issue time, and forecast-circle centers, radii and times, relayed as structured JSON from JMA bulletins (VPTW60-65). No independent forecast, interpolation or track extension.

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`note`	Yes
`count`	Yes
`ended`	Yes
`terms`	Yes	URL of the terms of service.
`source`	Yes	Data source and processor.
`status`	Yes	listed = JMA is issuing typhoon bulletins; none_in_checked_sources = none in the checked feeds; partial/unknown = some or all could not be checked.
`typhoons`	Yes
`unchecked`	Yes
`provenance`	Yes	Freshness receipts for every upstream source used.
`license_note`	Yes
`responded_at`	Yes
`retrieved_at`	Yes	When the upstream data was retrieved (ISO 8601).
`checked_sources`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 11, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "checked_sources": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "count": {
+      "type": "number"
+    },
+    "ended": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "license_note": {
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "provenance": {
+      "description": "Freshness receipts for every upstream source used.",
+      "items": {
+        "additionalProperties": {},
+        "description": "Freshness receipt for one upstream source.",
+        "properties": {
+          "content_sha256": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "fetch_status": {
+            "description": "found / empty / stale / unavailable / unsupported (see catalog fetch_status_values).",
+            "enum": [
+              "found",
+              "empty",
+              "stale",
+              "unavailable",
+              "unsupported"
+            ],
+            "type": "string"
+          },
+          "parser_version": {
+            "type": "string"
+          },
+          "processed_by": {
+            "type": "string"
+          },
+          "retrieved_at": {
+            "description": "When this service retrieved the upstream data (null if unknown).",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "source": {
+            "additionalProperties": {},
+            "description": "Publisher and URL of the upstream document or dataset.",
+            "properties": {
+              "publisher": {
+                "type": "string"
+              },
+              "url": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "publisher",
+              "url"
+            ],
+            "type": "object"
+          },
+          "upstream_updated_at": {
+            "description": "Update time stated by the upstream, or null when it states none.",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "source",
+          "upstream_updated_at",
+          "retrieved_at",
+          "content_sha256",
+          "parser_version",
+          "fetch_status",
+          "processed_by"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "responded_at": {
+      "type": "string"
+    },
+    "retrieved_at": {
+      "description": "When the upstream data was retrieved (ISO 8601).",
+      "type": "string"
+    },
+    "source": {
+      "description": "Data source and processor.",
+      "type": "string"
+    },
+    "status": {
+      "description": "listed = JMA is issuing typhoon bulletins; none_in_checked_sources = none in the checked feeds; partial/unknown = some or all could not be checked.",
+      "enum": [
+        "listed",
+        "none_in_checked_sources",
+        "partial",
+        "unknown"
+      ],
+      "type": "string"
+    },
+    "terms": {
+      "description": "URL of the terms of service.",
+      "type": "string"
+    },
+    "typhoons": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "issued_at": {
+            "type": "string"
+          },
+          "slot": {
+            "type": "string"
+          },
+          "source_url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "slot",
+          "issued_at",
+          "source_url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "unchecked": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "reason": {
+            "type": "string"
+          },
+          "slot": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "slot",
+          "reason"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "status",
+    "count",
+    "typhoons",
+    "ended",
+    "unchecked",
+    "checked_sources",
+    "note",
+    "provenance",
+    "source",
+    "retrieved_at",
+    "responded_at",
+    "license_note",
+    "terms"
+  ],
+  "type": "object"
+}

First observedOct 11, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With readOnlyHint and openWorldHint already declaring the safety and external-data profile, the description adds real value: the upstream provenance (JMA bulletins VPTW60-65) and the explicit statement that no independent forecast, interpolation or track extension is performed. That provenance/scope disclosure goes beyond what annotations provide.

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?

A single dense sentence, front-loaded with the scoping question and followed by the returned fields, with no filler. The enumerated return fields duplicate what the output schema already provides, costing a little space.

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?

Zero parameters and an output schema mean the description need not explain invocation or return shapes, and it covers provenance and no-derivation limits. It stops short of noting bulletin update cadence or that 'right now' reflects the latest JMA issuance rather than live tracking.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The field list in the description actually describes outputs rather than inputs, which is redundant with the output schema but not harmful.

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?

The description states a specific resource (JMA typhoon bulletins) and enumerates exactly what is returned: number, name, center position, pressure, max wind, issue time, forecast circles. This clearly separates it from jp_volcanoes and jp_warnings by resource, though it never names those siblings explicitly.

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?

Usage is implied by the framing question ('which typhoons is JMA issuing bulletins for right now') and constrained by 'No independent forecast, interpolation or track extension', which tells the agent this is a relay only. However, no alternative tool is named and no explicit condition for choosing this over, e.g., jp_warnings is given.

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

All Japan Agent API 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.

Resources

Need Help?