Skip to main content
Glama

search_literature

Read-onlyIdempotent

Search publications and preprints in Europe PMC (PubMed, PMC, bioRxiv and others).

query: free text or Europe PMC syntax (e.g. 'grain size QTL 6A', 'TITLE:"pan-genome"'). gene: optional gene name or Ensembl ID; its curated synonyms and RefSeq IDs are OR-ed into the query (e.g. gene='GLYMA_01G000600'). Words are matched in title and abstract; full_text=True also searches open-access full text. crop_only requires a legume crop or genus name in title or abstract. sort: 'relevance', 'date' (newest first) or 'cited'. Returns hit count and papers with DOI/PMID, year, journal, open-access flag, citations and a short abstract.

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": {
      "query": "<query>"
    },
    "name": "search_literature"
  }
}

Input Schema

NameRequiredDescriptionDefault
geneNo
sortNorelevance
limitNo
queryYes
crop_onlyNo
from_yearNo
full_textNo
open_access_onlyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, openWorld, idempotent, non-destructive), and the description adds genuinely new behavior: matching happens in title and abstract, full_text extends into open-access full text, crop_only restricts results to legume crop/genus terms (notably defaulting to true, which materially narrows results), and the sort options are spelled out. It also describes the return payload (hit count, DOI/PMID, year, journal, OA flag, citations, short abstract), which matters since no output schema exists. Missing only operational caveats such as rate limits or index coverage dates.

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?

Front-loaded with the one-line purpose, then a compact per-argument list with concrete examples and no redundant restatement of the tool name. Every line adds information an agent would otherwise have to guess.

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 an 8-parameter tool with no schema documentation and no output schema, this is close to self-sufficient: it covers the high-semantics parameters, the return fields, and the surprising crop_only default. The omissions (limit, from_year, open_access_only semantics) are minor but leave the agent guessing on date filtering, which is a common search need.

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 0% schema description coverage, the description carries the full burden and mostly succeeds: it explains the query syntax with examples, discloses that gene synonyms and RefSeq IDs are OR-ed into the query (a non-obvious expansion unavailable from the schema), and enumerates the sort values that the schema leaves unconstrained. limit, from_year, and open_access_only are undocumented, which is a real gap at 8 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with its source scope: 'Search publications and preprints in Europe PMC (PubMed, PMC, bioRxiv and others)'. An agent immediately knows this is literature retrieval rather than the data/gene tools among the siblings. It stops short of naming a sibling such as get_paper for retrieving a single known article.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage guidance is present but is parameter-level (when to add a gene, when to set full_text, what crop_only enforces) rather than tool-level. There is no statement of when to prefer this tool over alternatives like get_paper for a specific record, nor any exclusion such as 'do not use for sequence lookups'. Usage is implied rather than routed.

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