Skip to main content
Glama

Citation Integrity Report (paid, large tier)

citation_report_large

Verify a bibliography. For every reference: exists, resolves, retracted/corrected/flagged, title/author/year match against the registered record, and a rule-derived fabrication risk — as a signed (Ed25519, RFC 8785 canonical JSON), byte-reproducible JSON report. Input: structured references or BibTeX. No LLM; every claim carries its source and retrieval time. Up to 70 references. Paid: $3.00 USDC per successful call via x402 (eip155:8453). An unpaid call returns the payment requirements (isError). Results carry settled / transaction / network / payer plus the signed report. Use this to check references you already have; to find papers for a question or claim, use evidence_pack_preview / evidence_pack instead. NOTE: $3.00 is above the @x402/core client's default spend cap (maxAmountPerPayment $1.00); raise it (client.setSpendControls) before calling, or the client refuses without sending anything.

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": "citation_report_large"
  }
}

Input Schema

NameRequiredDescriptionDefault
bibtexNoA BibTeX bibliography (entry key → reference id); at most 262144 UTF-8 bytes — maxLength counts characters and is exact for ASCII.
optionsNo
referencesNoStructured references. Exactly one of references / bibtex.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / bibtex / description
      Previous value: -"A BibTeX bibliography (entry key → reference id)."New value: +"A BibTeX bibliography (entry key → reference id); at most 262144 UTF-8 bytes — maxLength counts characters and is exact for ASCII."
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses cost and payment rail ($3.00 USDC via x402 on eip155:8453), what an unpaid call returns, that billing is per successful call, that results include settled/transaction/network/payer settlement metadata, that the report is Ed25519-signed over RFC 8785 canonical JSON and is byte-reproducible, that no LLM is involved and every claim carries source and retrieval time, and a hard limit of 70 references.

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?

Purpose is front-loaded, followed by payment mechanics, then the sibling redirect, then the spend-cap caveat — the ordering serves the agent well and essentially every sentence adds information. It is nonetheless a dense wall of clauses, and the tier/limit information is buried mid-paragraph rather than stated once up front.

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?

With no output schema and nested parameters, the description does the heavy lifting: it describes the settlement envelope (settled / transaction / network / payer) returned alongside the signed report and enumerates the per-reference checks the report encodes. The remaining gap is that the report's actual field structure and how per-reference verdicts/fabrication-risk scores are represented is not described anywhere.

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?

The description tells the agent the two accepted input shapes ('structured references or BibTeX') and a size limit, which adds some value over a 67%-covered schema. But it does not explain the 'options' object (strict_authors, include_unpaywall are undocumented in both schema and description), and 'Up to 70 references' conflicts with the schema's maxItems: 200 for references, leaving the agent unsure which cap governs and risking an over-limit paid call.

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 ('Verify a bibliography'), then enumerates exactly what is checked per reference (existence, resolution, retraction/correction flags, title/author/year match, fabrication risk) and the output form (signed, byte-reproducible JSON). It also names sibling tools (evidence_pack_preview / evidence_pack) that serve the different job of finding papers, so the agent can separate the two without opening schemas.

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?

Explicit routing guidance: 'Use this to check references you already have; to find papers for a question or claim, use evidence_pack_preview / evidence_pack instead.' It also gives an operational prerequisite before calling (the $3.00 price exceeds the @x402/core default maxAmountPerPayment of $1.00, so raise it via client.setSpendControls or the client refuses locally) and clarifies that an unpaid call returns payment requirements as isError rather than doing work.

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