Skip to main content
Glama

jp_lit_refine_results

Refine saved search results by sorting, filtering, and performing set operations locally. Optionally retrieve duplicate clusters with cached enrichment, without re-querying external databases.

Instructions

read-only。保存済み jp_lit_search 結果を upstream 再検索せずローカルでソート・フィルタ・集合演算し、必要時だけ重複候補クラスタも返す。include_enrichment=true なら保存済み jp_lit_enrich_record cache を cluster に重ねるが、Crossref/OpenAlex へ新規照会しない。cache_key が分かっている結果を再評価するときに使い、cache_key を探す段階では jp_lit_search_cache_index または jp_lit_list_cache を使う。cache や session は変更しない

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo返す item の最大件数。最大 200。
key_byNo集合演算時に item を同一視するキー。source_record は source+source_id、duplicate_key は正規化重複キー、title_author_year はタイトル著者年。source_record
offsetNo返す item の offset。0 始まり。
combineNo複数 cache の集合演算。union は和集合、intersection は積集合、minus は先頭から後続を除外する。union
filtersNo保存済み結果に対するローカル filter。upstream 再検索は行わない。
sort_byNo再抽出結果の並び替え項目。未指定なら元の順序を保つ。
cache_keyNo再抽出する単一の jp_lit_search cache_key。cache_keys と同時指定しない。
cache_keysNo集合演算する複数の jp_lit_search cache_key。
session_idNoセッションに紐づく検索 cache を対象にする場合のセッションID。
sort_orderNosort_by 指定時の並び順。asc
cluster_limitNo返す重複クラスタの最大件数。
cluster_offsetNo重複クラスタ一覧の offset。0 始まり。
include_enrichmentNotrue の場合は保存済み jp_lit_enrich_record cache を読み、重複クラスタに外部書誌照合 metadata を付与する。外部 API は呼ばない。
cluster_member_limitNo各重複クラスタで preview する member の最大件数。
enrichment_cache_keysNocluster enrichment に使う jp_lit_enrich_record cache_key。未指定なら対象 session の jp_lit_enrich_record 履歴を使う。
include_duplicate_clustersNotrue の場合は重複候補クラスタを追加で返す。

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYes
limitYes
key_byYes
offsetYes
combineYes
clustersNo
total_afterYes
total_beforeYes
base_cache_keyYes
totals_by_baseYes
base_cache_keysYes
cluster_summaryNo
Behavior5/5

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

With no annotations, the description fully discloses behavioral traits: it is read-only, does not call external APIs (not even Crossref/OpenAlex for enrichment), only reads cached data, and does not modify cache or session. This provides complete transparency for safe invocation.

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?

The description is a single, concise paragraph front-loaded with 'read-only'. It efficiently covers purpose, enrichment detail, usage guidance, and side-effect disclaimer without waste.

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?

Given the tool's complexity (16 parameters, nested objects) and the existence of an output schema, the description captures the key operational behavior and usage context. It could clarify the order of operations between filters and set operations, but overall it is adequate.

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 schema already provides 100% coverage with detailed descriptions. The description adds value by explaining the enrichment behavior (include_enrichment reads cache without external calls) and the cache_key usage context, going beyond 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 refines saved jp_lit_search results locally without upstream re-search, performing sort, filter, set operations, and optionally returning duplicate clusters. It distinguishes from siblings by mentioning when to use jp_lit_search_cache_index or jp_lit_list_cache for finding cache keys.

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?

Explicitly specifies when to use this tool (when cache_key is known) and when to use alternatives (to find cache keys: jp_lit_search_cache_index or jp_lit_list_cache). Also implies it is for refining after initial search.

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