Skip to main content
Glama

PaperList

Search papers

search_papers
Read-onlyIdempotent

Full-text search over titles, abstracts, keywords and authors. Quoted phrases stay exact; OR / AND / NOT and parentheses are supported; common ML acronyms (JSCC, RAG, RLHF, VLA, VLM, DPO, MoE, ...) are expanded. Filter by conference slugs, year range (include year 2027 for ICLR 2027 under-review submissions), acceptance type, topic slug, or author name (must match one author). Defaults to slim rows (id, title, venue, year, decision, rating, url) so clients can scan many papers; pass fields=full or call get_paper/fetch for abstracts. If no paper matches enough of the query, the response is empty or clearly marked as a looser fallback, rather than off-topic any-word hits.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_papers"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
limitNoResults per page. slim: search up to 200 (default 10), list_papers up to 250 (default 100). full: 1-25 (default 10).
queryNoSearch words. Quoted phrases stay exact; OR / AND / NOT and parentheses work. Common acronyms (JSCC, RAG, RLHF, VLA, VLM, DPO, MoE, ...) are expanded.
topicNoTopic slug from list_conferences topics_for (use iclr2027-* for ICLR 2027 primary areas)
authorNoAuthor name, e.g. "Kaiming He". Must match tokens of one author name.
cursorNonext_cursor from a previous call
fieldsNoslim (default for list_papers/search_papers/find_similar_papers) returns id, title, conference, year, decision, rating_avg, url, and short topics. Use full or get_paper/fetch for abstracts. Prefer slim when scanning or exporting a conference.
year_toNo
decisionNoAcceptance types to keep (case-insensitive exact match). Common values: Oral, Spotlight, Poster, Highlight, Findings, Main; ICLR 2027 also uses Under review, Desk reject, Withdrawn.
year_fromNoInclude ICLR 2027 under-review submissions only when the year range overlaps 2027.
conferencesNoConference slugs from list_conferences, e.g. ["iclr", "neurips"]

Output Schema

NameRequiredDescriptionDefault
noteNo
yearNo
totalNo
fieldsNo
papersYes
conferenceNo
next_cursorYesPass as cursor to get the next page; null when there are no more results.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

The annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real behavioral value beyond that: query operator semantics, acronym expansion, and the important guarantee that low-fit queries return empty or a clearly marked looser result rather than off-topic any-word hits. It says nothing about result ordering despite a sort parameter, which is the remaining behavioral gap.

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?

Dense but front-loaded: search scope first, then query syntax, then filters, then defaults and alternatives. Some phrases (acronym expansion list) duplicate the query parameter's schema description, and the long semicolon chain is harder to scan than a short bulleted structure, but nothing is pure filler.

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?

An output schema exists, so return values need no explanation, and the description still usefully summarizes the slim row shape and points to get_paper/fetch for deeper reads. For an 11-parameter, zero-required search tool, the only meaningful omissions are result ordering and pagination behavior, both partially covered by schema descriptions.

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 82%, so the baseline is 3; the description still earns credit by adding meaning the schema does not: filtering by conference slugs, the year_from caveat that year 2027 is needed for ICLR 2027 under-review submissions, acceptance types, topic slugs, and the rule that author must match one author. The uncovered area is sort, which is unexplained in both the schema and the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource plus the exact index covered: 'Full-text search over titles, abstracts, keywords and authors.' It also implies its position relative to get_paper/fetch (which serve abstracts) and list_papers (via the fields/limit notes). It never contrasts with the sibling named 'search', so an agent facing both must infer the difference.

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 clear operating context: it describes the default slim row projection, says to pass fields=full or call get_paper/fetch when abstracts are needed, and explains the fallback semantics for weak matches. It does not state when to avoid this tool in favor of list_papers, find_similar_papers, or the generic 'search'.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources