Skip to main content
Glama

Recommend related papers

recommend_papers
Read-onlyIdempotent

Papers related to one or more origin papers, found through their citation network (co-citation and bibliographic coupling). Pass Paper Nexus ids from search_papers, or papernex.us/paper/ links. Several origins merge their related papers, with papers related to more than one of them first; origins from unrelated fields give a mix of each field's papers, not papers bridging them. Results are listed most related first: the order weighs how strongly each paper is linked to the origins (for well-connected origins, over a sample of their citers and references) and, without filters, also damps very highly cited papers and lifts recent ones. It orders this one list; it is not a probability of relevance or a measure of scientific importance. Each paper's evidence gives the citation links behind it, with link_counts saying how many co-citations and shared references link it to each origin, out of what each origin's sampled says was read: weigh a paper held up by few of them accordingly. graph_url opens the whole graph in Paper Nexus, which can hold more papers than limit. Pass fields to get only the details of each paper you need. With filters, every related paper passes them, best match first; years are the only date precision. To keep to papers linked to every origin, pass the origins as filters.cites with cites_match "all" (papers citing all of them), or narrow by topic with filters.title.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "papers": "<papers>"
    },
    "name": "recommend_papers"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
fieldsNoOnly these fields of each paper, to keep the result short; the id always comes back. Leave it out for every field.
papersYesPaper Nexus paper ids, or papernex.us/paper/<id> links
filtersNoOnly return papers that pass every filter given here. The search goes deeper than the plain recommendations to fill the list, so pass filters here rather than filtering the results yourself.

Output Schema

NameRequiredDescriptionDefault
filtersNoThe filters applied, as understood
originsYes
graph_urlYes
not_foundNo
filter_summaryNo
recommendationsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the read-only, idempotent annotations, the description discloses rich behavioral details: how origins are merged, how results are ordered, that the ranking damps highly cited papers and lifts recent ones, that it is not a probability of relevance, and how evidence and link_counts should be interpreted. These are exactly the kind of operational nuances an agent needs before invoking the tool.

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 front-loaded with purpose and core behavior, and most sentences carry useful information. It is dense and could be easier to scan with bullets, but the length is justified by the tool's complexity and the need to explain ranking and filter semantics.

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 complex citation-network behavior, nested filters, output schema, and strong annotation coverage, the description is complete enough for an agent to invoke the tool correctly. It covers input sourcing, merging, ordering, evidence interpretation, graph output, field selection, and filter behavior.

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 documents 75% of parameters, but the description adds useful semantics: it explains that `fields` narrows returned details, that `filters` are applied by the search engine rather than post-filtering, and that origins can be passed through `filters.cites` with `cites_match: "all"` to keep papers linked to every origin. It does not explain every filter parameter, but it materially clarifies the most important ones.

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 states a specific verb and resource: it returns papers related to origin papers through their citation network, specifically co-citation and bibliographic coupling. This method-level framing clearly distinguishes it from sibling tools such as list_citing_papers, which handles direct citations.

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?

It gives clear usage context by telling the agent to pass Paper Nexus ids from search_papers or papernex.us links, and explains how multiple origins merge and how filters should be applied. However, it does not explicitly name when to prefer or avoid the sibling list_citing_papers tool, leaving that comparison implicit.

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