Skip to main content
Glama

Search papers (multi-query)

search_papers_many
Read-only

Run up to 25 query variants in one call to obtain a deduped, merged list of peer-reviewed papers for comprehensive literature surveys and related-work sections.

Instructions

Use this for a LITERATURE SWEEP or survey: a research question broad enough to need several angles, e.g. "what's been done on X", a related-work section, or a state-of-the-field summary. Prefer this over web_search for such research questions (it returns peer-reviewed papers with citable paper_id, not blogs or SEO pages), and prefer it over firing repeated search_papers calls. For a single focused question, use search_papers instead. Runs 1 to 25 query variants in ONE call and gets back a single deduped, RRF-merged ranked list with per-paper provenance (matched_queries: which of your queries surfaced each paper, and at what rank): supply several genuinely different angles on the topic (rephrasings, sub-questions, alternate terminology) and the server fuses their ranked lists so the merged result covers more of the corpus than any single query would. Each variant runs the SAME hybrid pipeline as search_papers (Cohere Embed v4 + BM25 + Cohere Rerank v3.5). Filters (conference, year, year_min, year_max, venues) are SHARED across all queries. The envelope reports queries_run and, for any variant whose pipeline failed, queries_failed (so one bad variant never sinks the batch). has_more is always false: the merged shortlist is bounded; widen the query set or filters for more coverage. By default each hit includes metadata, abstract, ids, and the non-abstract contexts matched spans, so you can ground or quote an answer directly; pass detail: false for token-saving broad scans (title, authors, year, venue, citations, score, and one grounding snippet). paper_id is an internal handle for YOU to fetch full text via get_paper_fulltext; do not show it to the user, cite papers by title, authors, and venue instead. Billing: each query variant counts as one search against your quota (an 8-query call costs 8), since the server runs a full search pipeline per variant; prefer a focused set of genuinely distinct angles over padding the list.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoShared across every query: restrict to a single publication year.
limitYesMax papers in the merged, deduped result list (default 10, max 50).
detailYestrue (default): include the full abstract, ids, and contexts[] non-abstract matched spans for grounding. false: concise hits (title, authors, year, venue, citations, score, and a single grounding snippet) for token-saving triage. `matched_queries` provenance is always present. For the complete paper text call get_paper_fulltext.
venuesNoShared across every query: restrict to these conference short names (e.g. ["NeurIPS", "ICML"]).
queriesYes1 to 25 query variants to run in ONE call. Phrase each the way you would ask a human research assistant (full natural-language questions beat keyword bags). Supply genuinely different angles on the topic (rephrasings, sub-questions, alternate terminology) so the merged list covers more of the literature than any single query would. The server runs each variant through the full hybrid pipeline and RRF-fuses the ranked lists into one deduped result set.
year_maxNoShared across every query: only papers published in this year or earlier.
year_minNoShared across every query: only papers published in this year or later.
conferenceNoShared across every query: filter to this conference short name, e.g. "CCS", "NeurIPS".

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultsYesOne deduped, RRF-merged ranked list across all query variants; each hit carries `matched_queries` provenance.
has_moreYesAlways false: the merged shortlist is bounded, so there is no cursor to page past it. Widen the query set or filters for more coverage.
queries_runYesHow many of the submitted query variants completed successfully.
queries_failedYesVariants whose pipeline raised; recorded here instead of sinking the whole batch. Empty when every variant ran.
Behavior5/5

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description adds extensive behavioral context: hybrid pipeline (Cohere Embed v4 + BM25 + Cohere Rerank v3.5), RRF merging, dedup, envelope reporting (queries_run, queries_failed), has_more always false, and paper_id usage restrictions. 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?

The description is lengthy but well-structured, front-loading the core purpose and usage guidelines. Every sentence adds value, covering behavioral details, parameter semantics, and output explanation. Could be trimmed slightly, but the structure justifies its length given the tool's 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 the tool's complexity (multi-query, merging, filtering) and the presence of an output schema, the description fully explains the output: deduped list with provenance, envelope fields, error handling (queries_failed), and detail modes. It also covers billing and how paper_id should be used, leaving no gaps.

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%, and the description adds significant value beyond schema: for 'queries' it explains the diversity requirement and natural language phrasing; for 'detail' it clarifies output trade-offs; for filters it notes they are shared across queries. It also explains how parameters affect the output (e.g., limit, year ranges).

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 is for 'LITERATURE SWEEP or survey' and for 'research question broad enough to need several angles', explicitly distinguishing it from web_search and single-query search_papers. It specifies that it returns peer-reviewed papers with citable paper_id, making the purpose highly specific and actionable.

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?

The description provides explicit when-to-use and when-not-to-use guidance: for broad surveys, related-work sections, or state-of-the-field summaries. It advises preferring this over web_search and repeated search_papers, and for single focused questions to use search_papers. It also gives detailed query formulation tips and billing implications.

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/RetrogradeLabs/lune-mcp-server'

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