Japanese Skills · 言の葉

Words that use a kanji

lookup_kanji

Read-onlyIdempotent

Use this when the user asks about a kanji (a Chinese character used in Japanese): which JLPT words use it and how it is read in them, at which JLPT level it first appears, or where to learn it. For each kanji given (up to five), lists the words in the site’s JLPT word list that contain it, easiest level first, with reading, level and meaning in the user’s language; how many words use it and the lowest level among them; and the site’s kanji lessons that teach it (title, link, and whether each is free or needs a subscription or pass). Gives no on’yomi/kun’yomi table or stroke order: the readings are those of the words.

Input Schema

Name	Required	Description
`lang`	No	The user’s language for meanings, labels and links: zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), en (English) or ko (Korean). Other languages: en. Default: guessed from the query.
`kanji`	Yes	One to five kanji, e.g. "生" or "日本".
`limit`	No	How many words to list per kanji at most.

Output Schema

Name	Required	Description	Default
`lang`	Yes
`kanji`	Yes
`credit`	No
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "credit": {
+      "type": "string"
+    },
+    "kanji": {
+      "type": "string"
+    },
+    "lang": {
+      "enum": [
+        "zh-Hans",
+        "zh-Hant",
+        "en",
+        "ko"
+      ],
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "properties": {
+          "count": {
+            "type": "integer"
+          },
+          "kanji": {
+            "type": "string"
+          },
+          "lessons": {
+            "items": {
+              "properties": {
+                "course": {
+                  "type": "string"
+                },
+                "free": {
+                  "description": "false: needs a subscription or pass",
+                  "type": "boolean"
+                },
+                "lesson": {
+                  "type": "integer"
+                },
+                "title": {
+                  "type": "string"
+                },
+                "url": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "course",
+                "lesson",
+                "title",
+                "free",
+                "url"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "lowestLevel": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "words": {
+            "items": {
+              "properties": {
+                "level": {
+                  "description": "JLPT level: N5 (easiest) to N1",
+                  "type": "string"
+                },
+                "meaning": {
+                  "type": "string"
+                },
+                "reading": {
+                  "type": "string"
+                },
+                "url": {
+                  "type": "string"
+                },
+                "word": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "word",
+                "reading",
+                "level",
+                "meaning",
+                "url"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          }
+        },
+        "required": [
+          "kanji",
+          "count",
+          "lowestLevel",
+          "words",
+          "lessons"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "kanji",
+    "lang",
+    "results"
+  ],
+  "type": "object"
+}

First observedOct 26, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses hard operational limits (up to five kanji, easiest level first) and, most usefully, the negative space: 'Gives no on'yomi/kun'yomi table or stroke order: the readings are those of the words.' That prevents a very likely misuse (expecting a dictionary-style reading table).

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?

Front-loaded with the activation condition and no filler sentences. The second sentence is a long enumerated run-on, but each clause maps to a real output component or constraint, so nothing is wasted.

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?

Complete for a read-only lookup: trigger conditions, per-kanji output contents, ordering, count/lowest-level summary, lesson metadata with access status, plus explicit exclusions. An output schema exists, so the return-value prose is redundant but harmless.

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 earns above that by restating the 'up to five' kanji cap and clarifying that readings/meanings come back in the user's language, which makes the lang parameter's effect concrete rather than just an enum label.

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?

States a specific verb+resource (lookup_kanji) and enumerates exactly what is returned: JLPT words containing the kanji, readings, first-appearance level, and lesson links. It also carves out the scope against a word/grammar lookup by framing the trigger as 'the user asks about a kanji' rather than about a word.

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?

'Use this when the user asks about a kanji... which JLPT words use it and how it is read in them, at which JLPT level it first appears, or where to learn it' gives three concrete activation triggers. It does not explicitly name lookup_word as the alternative for word-level queries, so the closest sibling distinction is left implicit.

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

All Japanese Skills · 言の葉 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?