Skip to main content
Glama

Folklore Clinical Variant Interpretation MCP

Get details for a PubMed publication

get_publication_details
Read-onlyIdempotent

Retrieve one publication from Folklore's PubMed-derived genetics corpus, including title, abstract, authors, journal, publication types, MeSH terms, gene and variant mentions, retraction status and PubMed/PMC links. Pass exactly {"pmid":"12345678"}, using a PMID returned by search_variant_literature or search_literature_corpus. The pmid must be a string of 1 to 12 ASCII digits, not a number, URL, DOI or PMID-prefixed label. This is a corpus lookup, not a lookup of every PubMed record. On publication_not_found, do not retry the same PMID; search_literature_corpus can find available records.

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": {
      "pmid": "<pmid>"
    },
    "name": "get_publication_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
pmidYesOne PMID returned by Folklore literature search, as a JSON string of 1 to 12 ASCII digits. Do not send a number, PMID prefix, URL or DOI. The current corpus does not contain every PubMed record.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / pmid / description
      Previous value: -"One PubMed identifier to look up in Folklore's current corpus, as 1 to 12 digits without a PMID prefix."New value: +"One PMID returned by Folklore literature search, as a JSON string of 1 to 12 ASCII digits. Do not send a number, PMID prefix, URL or DOI. The current corpus does not contain every PubMed record."
  2. Changed5 schema fields changed
    • removedOutput schema / additionalProperties
      Removed value: -false
    • addedOutput schema / anyOf
      Added value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "contract_version": {
      +        "const": "2",
      +        "title": "Contract Version",
      +        "type": "string"
      +      },
      +      "publication": {
      +        "$ref": "#/$defs/PublicPublicationDetails"
      +      }
      +    },
      +    "required": [
      +      "contract_version",
      +      "publication"
      +    ],
      +    "title": "PublicationDetailsResponse",
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "adapter_error": {
      +        "anyOf": [
      +          {
      +            "additionalProperties": false,
      +            "properties": {
      +              "code": {
      +                "minLength": 1,
      +                "type": "string"
      +              },
      +              "message": {
      +                "minLength": 1,
      +                "type": "string"
      +              },
      +              "retryable": {
      +                "type": "boolean"
      +              }
      +            },
      +            "required": [
      +              "code",
      +              "message",
      +              "retryable"
      +            ],
      +            "type": "object"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "contract_version": {
      +        "const": "2",
      +        "type": "string"
      +      },
      +      "record_url": {
      +        "format": "uri",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "result": {
      +        "anyOf": [
      +          {
      +            "additionalProperties": true,
      +            "properties": {
      +              "search_contract_version": {
      +                "const": "1.0",
      +                "type": "string"
      +              },
      +              "status": {
      +                "enum": [
      +                  "resolved",
      +                  "ambiguous",
      +                  "not_found",
      +                  "invalid_request",
      +                  "unsupported",
      +                  "resolution_unavailable"
      +                ],
      +                "type": "string"
      +              }
      +            },
      +            "required": [
      +              "search_contract_version",
      +              "status"
      +            ],
      +            "type": "object"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      }
      +    },
      +    "required": [
      +      "contract_version",
      +      "record_url",
      +      "result",
      +      "adapter_error"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedOutput schema / properties
      Removed value: -{
      -  "contract_version": {
      -    "const": "1.0",
      -    "title": "Contract Version",
      -    "type": "string"
      -  },
      -  "publication": {
      -    "$ref": "#/$defs/PublicPublicationDetails"
      -  },
      -  "usage_boundary": {
      -    "additionalProperties": true,
      -    "title": "Usage Boundary",
      -    "type": "object"
      -  }
      -}
    • removedOutput schema / required
      Removed value: -[
      -  "contract_version",
      -  "publication",
      -  "usage_boundary"
      -]
    • removedOutput schema / title
      Removed value: -"PublicationDetailsResponse"
  3. Changed2 schema fields changed
    • addedOutput schema / $defs / PublicAbstractReuse
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "allowed": {
      +      "default": false,
      +      "title": "Allowed",
      +      "type": "boolean"
      +    },
      +    "evidence_url": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Evidence Url"
      +    },
      +    "license": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "License"
      +    },
      +    "source": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "title": "Source"
      +    }
      +  },
      +  "title": "PublicAbstractReuse",
      +  "type": "object"
      +}
    • addedOutput schema / $defs / PublicPublicationDetails / properties / abstract_reuse
      Added value: +{
      +  "$ref": "#/$defs/PublicAbstractReuse"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / pmid / description
      Added value: +"One PubMed identifier to look up in Folklore's current corpus, as 1 to 12 digits without a PMID prefix."
  5. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the description is free to add the parts annotations cannot express: the corpus is a subset of PubMed ("not a lookup of every PubMed record"), and the tool has a named error outcome (publication_not_found) with prescribed recovery behavior. That coverage-limit and error-semantics disclosure is exactly the behavioral context an agent needs to avoid misinterpreting an empty result as a missing paper.

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 the return payload, then constraints, then error handling — a sensible ordering with no filler sentences. It loses a point for restating the 1-to-12-ASCII-digit rule that the schema's pattern and property description already encode twice over.

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 an output schema present, the description does not need to explain return values yet still summarizes them for routing; with annotations covering safety, it focuses on corpus scope, input provenance and failure recovery. For a single-parameter lookup this leaves no meaningful gap for an agent deciding whether and how to call it.

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% and the pattern already enforces ^[0-9]{1,12}$, so the format warnings (not a number, URL, DOI or PMID-prefixed label) largely restate structured data. What the description adds beyond the schema is provenance — where a legitimate PMID comes from — which is the more actionable parameter guidance.

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 ("Retrieve one publication from Folklore's PubMed-derived genetics corpus") and enumerates what comes back — title, abstract, authors, journal, publication types, MeSH terms, gene/variant mentions, retraction status, PubMed/PMC links. This clearly separates it from the search_* siblings, which return result sets rather than a single record.

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?

Explicitly names the upstream tools that produce a valid PMID (search_variant_literature, search_literature_corpus) and gives a when-not-to-retry rule: on publication_not_found, fall back to search_literature_corpus rather than repeating the same PMID. Both the entry condition and the failure path are stated, not inferred.

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.