Skip to main content
Glama

jp_lit_search

Search across Japanese academic databases including NDL, CiNII, J-STAGE, and more. Cross-search 8 sources by default or specify targeted collections for dissertations, archives, and classical texts.

Instructions

日本語文献ポータルを検索する。source 未指定で8ソース横断。cinii_dissertations / national_archives / jacar / nijl_articles / kokusho / ninjal_bibliography は既定横断に含めず、博士論文・学位論文、公文書・外交・軍事・旧外地資料、国文学論文、古典籍、日本語研究文献などで明示指定された場合のみ使う。ユーザーの言い回しから source を読み替える: 「NDL/国会図書館」→ndl_catalog、「デジコレ/NDLデジタル」→ndl_digital、「CiNii論文」→cinii_articles、「博士論文/学位論文/CiNii Dissertations」→cinii_dissertations、「CiNii図書/大学図書館」→cinii_books、「J-STAGE」→jstage_articles、「機関リポジトリ/IRDB」→irdb、「国会会議録」→kokkai_minutes、「帝国議会」→teikoku_minutes、「人文専門DB/nihu_bridge」→nihu_bridge、「Japan Search/ジャパンサーチ」→japan_search、「国立公文書館/特定歴史公文書/太政官/省庁資料」→national_archives、「JACAR/アジア歴史資料/外交/軍事/旧外地/植民地/朝鮮/台湾/関東州」→jacar、「国文学論文/国文研論文/日本文学研究論文」→nijl_articles、「国書/古典籍/写本/版本」→kokusho、「日本語研究/日本語教育文献/国語教育文献」→ninjal_bibliography。total / limit / page はこの 1 回の検索呼び出し単位の値であり、Skill が複数回検索して要約する場合は各回ごとに読む。source=cinii_books では filters.cinii.category に NDC/NDLC notation を半角スペース区切りで渡せる。CiNii 系の 0 件・ローマ字 query・広すぎる結果では interpretation / diagnostics を読む。source=ndl_digital の結果にはインターネット非公開(館内限定・図書館送信)資料のメタデータも含まれる。OCR 系ツールを使う前に jp_lit_get_record で source_metadata.next_digital_library.available を確認すること

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo検索結果ページ番号。1 始まり。
limitNo1 回の検索で返す最大件数。最大 100。未指定時は source ごとの既定値を使う。
queryYes検索語。資料名、著者名、主題語、機関名などを指定する。
sourceNo検索対象 source。未指定なら既定の 8 source 横断検索になるが、新規テーマの初手では通常 ndl_search と japan_search などを明示指定する。
filtersNosource 固有の追加 filter。対象 source と一致しない filter は validation error になる。
sort_byNosource が対応する場合の並び替え項目。未対応 source では無視されることがある。
issued_toNo刊行年・日付の上限。issued_from と組み合わせて範囲指定する。
sort_orderNosort_by 指定時の昇順 asc / 降順 desc。
issued_fromNo刊行年・日付の下限。年だけの '1900' など source が扱う文字列表現で指定する。
force_refreshNotrue の場合はローカル cache を使わず upstream API から再取得する。false の場合は保存済み cache を優先する。

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageYes
cacheNo
itemsYes
limitYes
queryYes
totalYes
facetsNo
sourceYes
diagnosticsNo
interpretationNo
Behavior5/5

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

No annotations, so description carries full burden. Discloses cross-search behavior, source-specific behaviors (e.g., cinii_books category, ndl_digital internet non-public materials), handling of zero results, total/limit/page semantics, cache behavior (force_refresh), and interaction with get_record. No contradictions.

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 core purpose, then exceptions, mapping, and notes. Every sentence adds value, but the description is quite lengthy due to extensive mappings and usage details. Could be slightly more concise, but acceptable given complexity.

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?

Given 10 parameters, nested filters, 20 source options, and interactions with other tools (get_record, OCR), the description covers cross-search, source-specific filters, error conditions (zero results, validation), cache, and pagination semantics. Output schema exists, so return values are not needed. Highly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds significant value: user phrase-to-source mapping, explanation of filters being source-specific with validation errors, interpretation of issued_from/to as year strings, sort_by may be ignored, and cache control. These details are not in 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?

The description clearly states it searches a Japanese literature portal, with specific verb (検索する) and resource (日本語文献ポータル). It distinguishes from siblings by specifying default cross-source search and listing excluded sources, plus mapping from user phrases. No ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use: default cross-search vs explicit source specification. Details when not to use certain sources (cinii_dissertations etc.) unless explicitly specified. Provides mapping from user terms to source enums. Also advises on new topics to specify ndl_search and japan_search. Mentions alternative tools like jp_lit_get_record for digital availability. Comprehensive guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/itarunnn/jp-lit-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server