Skip to main content
Glama

Verify references

verify_references
Read-onlyIdempotent

Check every reference in a list against Crossref, PubMed and OpenAlex and report, for each one, whether the paper really exists and whether the details are right. Works on lists written by a person or generated by an AI model. Input: a pasted reference list in any common style (APA, Vancouver, numbered, mixed), BibTeX, RIS, CSL-JSON, or one DOI per line. Each reference gets exactly one status: verified, verified_with_corrections (real paper, some details wrong; corrected metadata included), likely_fabricated (the DOI is not registered or points to another paper, or the journal is indexed in these databases and no such paper is in it), not_found (could not be confirmed either way, for example a paper in a regional journal these databases do not cover), retracted, or ambiguous (several papers fit). Every unconfirmed reference lists the databases searched and how many records each returned, and the result carries the time of the check, so the verdict can be audited. likely_fabricated, not_found and ambiguous mean the reference could not be confirmed as a real paper; retracted means the paper exists but has been withdrawn. Retractions, expressions of concern and corrections are already checked here, so there is no need to call check_retractions on the same references afterwards. At most 50 references per call.

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": {
      "references": "<references>"
    },
    "name": "verify_references"
  }
}

Input Schema

NameRequiredDescriptionDefault
referencesYesThe reference list exactly as written: any citation style, BibTeX, RIS, CSL-JSON, or DOIs one per line.

Output Schema

NameRequiredDescriptionDefault
quotaYes
summaryYes
checked_atYesWhen the databases were queried (ISO 8601, UTC).
referencesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedOutput schema / properties / checked_at
      Added value: +{
      +  "description": "When the databases were queried (ISO 8601, UTC).",
      +  "type": "string"
      +}
    • addedOutput schema / properties / references / items / properties / searched
      Added value: +{
      +  "description": "For unconfirmed references: each lookup made, whether the database answered, and how many records it returned.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "answered": {
      +        "type": "boolean"
      +      },
      +      "database": {
      +        "type": "string"
      +      },
      +      "records": {
      +        "type": "integer"
      +      }
      +    },
      +    "required": [
      +      "database",
      +      "answered",
      +      "records"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "summary",
      -  "references",
      -  "quota"
      -]New value: +[
      +  "summary",
      +  "references",
      +  "checked_at",
      +  "quota"
      +]
  2. Changed1 schema field changed
    • addedOutput schema / properties / quota / properties / hint
      Added value: +{
      +  "enum": [
      +    "low",
      +    "intro"
      +  ],
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • addedOutput schema / properties / quota / properties / upgrade
      Added value: +{
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • changedOutput schema / properties / quota / properties / plan / enum
      Previous value: -[
      -  "anon",
      -  "free"
      -]New value: +[
      +  "anon",
      +  "free",
      +  "pro"
      +]
  5. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered; the description adds genuinely non-structured behavior: a per-call cap of 50 references, an auditable timestamp on the result, and per-database record counts for unconfirmed references. It does not describe latency or what happens when the same list is re-submitted (which the idempotent hint implies), leaving a small gap against the lower bar annotations set.

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?

It is front-loaded with purpose, then the status taxonomy, then the constraint, which is the right order for an agent. It is dense as a single paragraph and one sentence partly restates the status definitions already given ('likely_fabricated, not_found and ambiguous mean the reference could not be confirmed'), which is the only waste.

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?

An output schema exists, so return values need not be spelled out, yet the description still gives the full status vocabulary and explains what an unconfirmed result contains. Combined with the call limit and the sibling routing note, nothing an agent needs in order to call it correctly is missing.

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?

With a single parameter at 100% schema coverage, the baseline is 3; the description earns above that by enumerating the concrete input dialects (APA, Vancouver, numbered, mixed, BibTeX, RIS, CSL-JSON, one DOI per line) and by surfacing the 50-reference cap, a real constraint the schema's maxLength does not express.

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 opens with a specific verb and resource ('Check every reference in a list against Crossref, PubMed and OpenAlex') and states the output contract ('whether the paper really exists and whether the details are right'). It also differentiates itself from the sibling check_retractions by name, so an agent can route between them without opening either schema.

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?

It states the condition for use ('lists written by a person or generated by an AI model'), the accepted input forms, and an explicit exclusion routing rule: retractions and expressions of concern are already covered, so there is no need to call check_retractions afterwards. That is when-to-use, when-not-to-use, and the named alternative in one place.

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.