Skip to main content
Glama

Get citation edges

get_citation_edges
Read-onlyIdempotent

How a set of papers connect: which of them cite which, such as among related papers found earlier or a reading list. Pass 2 to 100 Paper Nexus ids or papernex.us/paper/ links, or DOIs, arXiv ids, PMIDs, PMCIDs or OpenAlex ids, as papers; each paper counts as one lookup. It returns only the citations between the papers given, each as citing and cited ids, with how many of the others each paper cites and is cited by, and the papers linked to none of them. The links come from reference lists (OpenAlex and Semantic Scholar): a link missing is not proof that one paper does not cite the other, and a citation alone does not show that one paper builds on the other. Pass fields to get only the details of each paper you need.

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": "get_citation_edges"
  }
}

Input Schema

NameRequiredDescriptionDefault
fieldsNoOnly these fields of each paper, to keep the result short; the id always comes back. Leave it out for every field.
papersYesPaper Nexus ids or papernex.us/paper/<id> links, or DOIs, arXiv ids, PMIDs, PMCIDs or OpenAlex ids

Output Schema

NameRequiredDescriptionDefault
edgesYesEach citation between two of the papers: citing cites cited
papersYesThe papers found, in the order given
completeNofalse when some pairs are unchecked
unlinkedNoThe papers that cite none of the others and that none cites
not_foundNoThe ids that are not Paper Nexus papers, left out
uncheckedNoPairs whose link is unknown: the citing paper has more than 600 references and the cited one more than 1000 citing papers, so Paper Nexus holds only part of each list
edge_countNo
identifiersNoWhen papers were named by DOI, arXiv id, PMID, PMCID or OpenAlex id: read_as maps each to its Paper Nexus id, and unresolved lists those no Paper Nexus paper has, which were left out

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, yet the description still adds real behavioral context: the cost model ('each paper counts as one lookup'), the provenance of links (OpenAlex and Semantic Scholar reference lists), and two caveats — a missing link is not proof of non-citation, and a citation does not imply the paper builds on the other. That is exactly the kind of nuance annotations cannot convey.

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?

Three sentences, front-loaded with the purpose before inputs, outputs, caveats, and the optional `fields` tip. Dense but every clause carries information; the closing sentence on `fields` is slightly tacked on but still earns its place.

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?

For a 2-parameter read tool with full schema coverage and an output schema, nothing material is missing: the agent knows what goes in, what comes back in general terms, what the call costs, and where the data comes from. The caveats about link absence and citation meaning preempt the most likely misreading of the results.

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 100%, so the baseline is 3; the description goes further by enumerating the accepted identifier formats and restating the 2-100 bound alongside their cost implication, and by explaining why `fields` exists (to keep results short, id always returned). It largely mirrors the schema's own text rather than adding new syntax detail.

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?

Opens with a concrete verb+resource framing: 'How a set of papers connect: which of them cite which.' The clause 'It returns only the citations between the papers given' semantically separates it from list_citing_papers and list_references, which work from a single paper. No sibling is named explicitly, so it falls just short of the top mark.

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?

'such as among related papers found earlier or a reading list' gives a concrete usage scenario, and the 2-100 input constraint with 'each paper counts as one lookup' tells the agent how costly a call is. There is no explicit when-not guidance or named alternative for the single-paper case, which keeps it below a 5.

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