japanlaw.org — Japanese law

Read one provision

get_provision

Read-onlyIdempotent

日本の法令の条・項・号の本文を読む。引用や説明の前に確かめる（改正で文言が変わっていることがある）。 Read the text of an article, paragraph or item of a Japanese law, to quote or explain it: the wording may have changed since a model learned it. One article, paragraph or item of a law, with everything under it. Call it with law and address: {"law": "labor-standards-act", "address": "art-36"}, or {"law": "労働基準法", "address": "第三十二条の三第一項"}. For each paragraph and item, the Japanese text (textJa), its English (textEn) and whose that English is (englishWhose: ministry — the Ministry of Justice's translation; corrected — the Ministry's with a slip this site corrected; machine — this site's machine translation, not official), and its url. Also the terms it defines, how many provisions it cites and how many cite it (references "lists" names them), and the official e-Gov page. A very long one — a big appended table, a 附則 of many articles — stops at a provision; continued.cursor, passed back as cursor with the same address, goes on from there. Shown to the reader as a card where the chat app can draw one. The text in force by default; asOf (a day) or version reads another text held — as it stood on a past day, or as an amendment not yet in force will leave it — and version says which text the answer is. Quoting it, link its url (the reader's page, with the English marked), not e-Gov's, and say whose English each quoted paragraph is.

Input Schema

Name	Required	Description
`law`	Yes	The law: its Japanese title (労働基準法), English title (Labor Standards Act), short name (労基法), slug (labor-standards-act) or e-Gov law ID (322AC0000000049).
`asOf`	No	Read the text as it stood on this day, YYYY-MM-DD (2027-04-01): past, today or to come. Unset reads the text in force. A day whose text japanlaw.org does not hold is refused as not held, with the texts that are; never answered with the nearest text.
`lang`	No	The language of the pages every url opens, and of the card get_provision is drawn as: "en" (default) or "ja". The text returned always holds both languages.
`cursor`	No	Go on from here: the cursor an earlier answer's continued gave, with the same address. Unset starts at the address.
`address`	Yes	The provision, as the statute writes it (第三十六条第二項第一号), as the Ministry's English does (Article 36(2)(i)), or as japanlaw.org does (art-36/par-2/item-1). A bare number is an article: 36. Supplementary provisions and appended tables use the site's addresses, which search and get_law hand out.
`version`	No	Read one held text by its version, as get_law's versions lists it (20270401_508AC0000000060). Unset reads the text in force. Pass asOf or version, not both.
`references`	No	"counts" (default): how many provisions this one cites and how many cite it. "lists": each of them too, with its url — the first 20 that cite it; get_citing_provisions has them all.

Output Schema

Name	Required	Description	Default
`url`	Yes
`path`	Yes
`lawId`	Yes
`provisions`	Yes
`pathLabelJa`	Yes
`permanentUrl`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 1, 2026

addedInput schema / properties / cursor

Added value: +{
+  "description": "Go on from here: the cursor an earlier answer's continued gave, with the same address. Unset starts at the address.",
+  "maxLength": 200,
+  "type": "string"
+}

removedInput schema / properties / from

Removed value: -{
-  "description": "Go on from this provision: the from an earlier answer's continued gave, with the same address. Unset starts at the address.",
-  "maxLength": 200,
-  "type": "string"
-}

addedInput schema / properties / references

Added value: +{
+  "description": "\"counts\" (default): how many provisions this one cites and how many cite it. \"lists\": each of them too, with its url — the first 20 that cite it; get_citing_provisions has them all.",
+  "enum": [
+    "counts",
+    "lists"
+  ],
+  "type": "string"
+}

First observedOct 31, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description layers on real behavioral detail: truncation at a provision with continued.cursor resumption, asOf refusal semantics ('never answered with the nearest text'), the englishWhose provenance taxonomy, and the citation rule to link the site url rather than e-Gov. That is context an agent could not infer from structured fields.

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?

Purpose is front-loaded and the later sentences on pagination, versioning and citation each carry distinct operational value. The Japanese and English purpose sentences say the same thing, which is pure duplication for a bilingual-capable model and the main thing keeping this from a 5.

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 seven-parameter tool with versioning, pagination and provenance subtleties, the description covers everything an agent needs to call it correctly and to use the answer responsibly. The return-value detail is arguably redundant against the output schema, but the englishWhose and citation guidance is not something the schema conveys.

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 a 3 is the floor, but the description adds genuine meaning: worked examples of both the slug and Japanese-address forms, the cursor round-trip ('continued.cursor, passed back as cursor with the same address'), and what references='lists' actually returns. It stops short of full coverage since asOf/version interactions are mostly restated from the schema.

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 and resource — 'Read the text of an article, paragraph or item of a Japanese law' — and immediately scopes it ('One article, paragraph or item of a law, with everything under it'), which distinguishes it from get_law (whole statute), get_definitions, and get_citing_provisions. An agent can route to it without opening the schema.

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 a concrete trigger ('to quote or explain it: the wording may have changed since a model learned it') and routes related needs to siblings ('get_citing_provisions has them all', 'search and get_law hand out' addresses). It never states an explicit when-not-to-use-this case, so it falls short of a 5.

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

All japanlaw.org — Japanese law 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?