Skip to main content
Glama

Pubtator Relations

pubtator_relations
Read-onlyIdempotent

List the relations PubTator 3 has extracted for a gene, disease, chemical or variant, which drugs treat a disease, which genes a disease is associated with, which chemicals inhibit a gene, ranked by supporting-publication count, each labelled machine-extracted, and the top relations carrying their supporting passages (the actual sentences, with PMIDs). Filter by relation type (treat, cause, associate, interact, inhibit, stimulate, prevent, positive/negative_correlate, cotreat, drug_interact, compare) and/or by a second entity. Accepts a PubTator id (@GENE_BRCA1) or a plain name. Sourced from the PubTator 3 relation-extraction model at NCBI/NLM, predictions from text, not curated. Keyless.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "treat",
      "limit": 10,
      "entity": "@CHEMICAL_Doxorubicin",
      "evidence_for": 2
    },
    "name": "pubtator_relations"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoRestrict to one relation type. Omit for all types.
limitNoMax relations to return, 1-50 (default 20).
entityYesThe entity to list relations for: a PubTator id ("@GENE_BRCA1", "@CHEMICAL_Doxorubicin") or a plain name ("BRCA1", "doxorubicin"), a name is resolved via autocomplete and reported in resolved_from.
targetNoOptional second entity to restrict to (id or plain name), e.g. "@DISEASE_Breast_Neoplasms".
evidence_forNoHow many of the top relations get supporting passages attached (one search each), 0-5 (default 3). Each attaches up to 3 passages with PMIDs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / entity / description
      Previous value: -"The entity to list relations for: a PubTator id (\"@GENE_BRCA1\", \"@CHEMICAL_Doxorubicin\") or a plain name (\"BRCA1\", \"doxorubicin\") — a name is resolved via autocomplete and reported in resolved_from."New value: +"The entity to list relations for: a PubTator id (\"@GENE_BRCA1\", \"@CHEMICAL_Doxorubicin\") or a plain name (\"BRCA1\", \"doxorubicin\"), a name is resolved via autocomplete and reported in resolved_from."
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, open-world, non-destructive, so the description is free to spend its words on what annotations cannot say: results are ranked by supporting-publication count, labelled machine-extracted, come from the PubTator 3 model at NCBI/NLM, are text-mined predictions rather than curated facts, and are keyless. It even discloses the cost of evidence_for ('one search each'). That is exactly the behavioral context an agent needs for trust calibration.

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 core action and the return shape, and every clause carries information. It is one very long compound sentence and partly re-enumerates the type enum already in the schema, which is modest redundancy.

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, the description carries the return-value burden and does so well: ranking basis, machine-extracted labelling, passage attachments with PMIDs, and resolved_from. It stops short of describing the response object's structure or fields, so an agent knows what to expect qualitatively but not the exact shape.

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%, so the baseline is 3; the description goes beyond it by listing all twelve relation types in prose, explaining that a plain name is resolved via autocomplete and reported in resolved_from, and stating that each evidence_for search attaches up to 3 passages with PMIDs (detail absent from the schema). Only minor value-add over the schema keeps it from a 5.

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?

Opens with a specific verb+resource ('List the relations PubTator 3 has extracted') and immediately enumerates the entity kinds and the question shapes it answers (drugs treating a disease, genes associated with a disease, chemicals inhibiting a gene). An agent can tell this apart from the annotation/search siblings without opening a schema.

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 clear operating context: filter by relation type (with 'Omit for all types'), filter by a second entity via target, and use evidence_for to pull supporting passages. It does not explicitly route the agent between this tool and pubtator_relation_evidence, which is the one guidance gap.

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.