Skip to main content
Glama

Quill Scholar Research Desk

Reference checker (catch hallucinated citations)

check_references
Read-only

Check up to 12 references (one per line, blank-line separated, BibTeX, or an array of strings) against arXiv, Crossref and DBLP. Each gets verified / verified_with_issues / partial_match / not_found, the problem (fabricated reference, DOI of a different paper, wrong year, wrong first author, garbled title, missing DOI), the canonical record and a corrected APA + BibTeX entry. Use it before you publish anything an AI helped write. Needs a Quill Research Pass (1 USDC = 24 h, 5 USDC = 7 days, 15 USDC = 30 days by plain USDC transfer on Base; see payment_options), or pay per call over HTTP x402 ($0.05) at /v1/refcheck.

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": {
      "refs": "<refs>"
    },
    "name": "check_references"
  }
}

Input Schema

NameRequiredDescriptionDefault
passNoOptional Quill Research Pass token (qp1...). Better: set it once as the MCP header Authorization: Bearer <token>.
refsYesReference list: one per line or blank-line separated, or BibTeX entries. Up to 12 references, 9000 characters. Omit for a demo. A string (one reference per line or blank-line separated, or BibTeX) or an array of strings.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: it discloses the verification status values returned, the failure modes detected (fabricated reference, DOI of a different paper, wrong year, garbled title), the access model (Quill Research Pass tiers with USDC transfer on Base) and the x402 per-call fallback price. None of this is inferable from the structured fields.

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?

Front-loaded with what the tool does, then the return values, then access requirements; each sentence carries information. The payment-pricing sentence is dense but relevant to invocation, and the only mild redundancy is repeating the reference formats already in the schema.

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?

With no output schema, the description carries the return-value burden and does so fully: per-reference status, problem diagnosis, canonical record, corrected APA and BibTeX. Authentication options (pass token header vs. x402) and the reference-count limit are also covered, leaving nothing an agent needs before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both refs and pass in detail. The description restates the accepted formats and the 12-reference ceiling but adds no new syntax or semantics beyond the schema, which is the expected baseline-3 case.

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?

States a specific verb and resource ('Check up to 12 references') plus the exact external sources consulted (arXiv, Crossref, DBLP) and the output taxonomy. It is unmistakable versus siblings like cite, literature_review, and search_papers, which do not verify existing reference lists against databases.

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 a clear use condition: 'Use it before you publish anything an AI helped write,' and points to payment_options for the access path. It does not state when NOT to use it (e.g., formatted citation generation vs. verification), so it stops short of full when/when-not/alternative guidance.

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