Skip to main content
Glama

verify_citations

Read-only

Verify up to 10 citations really exist and match the claimed title/authors/year, against Crossref, DataCite, arXiv and PubMed. Items: DOI, arXiv id, 'PMID: 123', free-text reference, or {doi|arxiv|pmid|title, authors, year}. Verdicts: verified, mismatch, not_found, error. Price: 0.01 USDC per call (x402, Base).

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": {
      "citations": "<citations>"
    },
    "name": "verify_citations"
  }
}

Input Schema

NameRequiredDescriptionDefault
citationsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint, the description discloses the external query surface, the full verdict taxonomy (verified, mismatch, not_found, error), the 10-item batch cap, and the per-call cost with payment protocol. Cost and payment rail are exactly the kind of behavioral fact annotations cannot express and that materially affect invocation decisions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compressed sentences that front-load the action and scope, then formats, then outcomes and price. No filler; the fragment style is dense but each clause contributes distinct information.

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?

For a single-parameter, paid, network-calling tool with no output schema, the definition covers inputs, sources, verdicts, and cost. It stops short of describing what a 'mismatch' verdict returns (which fields differ) or whether an 'error' verdict still incurs the 0.01 USDC charge, which are the remaining operational unknowns.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must carry parameter meaning and it does: it enumerates the exact string formats (DOI, arXiv id, 'PMID: 123', free-text) and the object keys that mirror the anyOf branches. An agent can construct a valid item without reverse-engineering the schema's maxLength/minItems constraints.

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?

Names a specific verb and resource ('Verify ... citations') plus the exact semantics of the check: existence plus match against claimed title/authors/year. The upstream sources (Crossref, DataCite, arXiv, PubMed) make it unambiguous versus siblings like verify_links, which operates on URLs rather than scholarly references.

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?

States the practical operating envelope clearly: up to 10 items per call, and the accepted input forms, so an agent knows when the tool applies. It does not explicitly state when NOT to use it or name an alternative (e.g., URL checking belongs to verify_links), so the routing guidance is implied by resource type rather than spelled out.

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