Skip to main content
Glama

x420_research_pubmed

Search PubMed literature and return up to 20 bibliographic citations with title, authors, journal, date, PMID, DOI, and links for research queries.

Instructions

PubMed literature search: Searches PubMed (NCBI E-utilities, free, no key) and returns up to 20 bibliographic records: title, authors, journal, date, PMID, DOI and links. Source: NCBI PubMed. Citations only, no abstracts; not medical advice. Not professional, legal, insurance, engineering, medical, financial or tax advice. PAID: $0.05 USDC per call, settled on Base via x402 from the wallet in X420_MCP_WALLET_PRIVATE_KEY (real money). Returns: JSON: total, count, results[{pmid, title, authors, journal, pubdate, doi, url}] - the deliverable plus X420's signed receipt and the settlement transaction. Example input: {"query":"hail storm injury","max":"1"}.

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": "x420_research_pubmed"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxNo1–20 results (default 10)
queryYesPubMed query, e.g. hail injury emergency department
min_yearNoearliest publication year (default: any)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.2

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing that each call costs $0.05 USDC settled on Base via x402 from X420_MCP_WALLET_PRIVATE_KEY, that it is real money, and what is returned (deliverable plus signed receipt and settlement transaction). This explains why readOnlyHint=false despite being a search, and warns the agent that calls are not free to retry.

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

Conciseness3/5

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

The key facts (source, limit, cost, return shape) are front-loaded, but the disclaimer text is redundant: "no abstracts; not medical advice" is immediately followed by "Not professional, legal, insurance, engineering, medical, financial or tax advice," restating the same point twice. Several sentences could be collapsed without losing 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?

With no output schema, the description carries the return contract and does so explicitly (total, count, results[{pmid, title, authors, journal, pubdate, doi, url}] plus receipt and settlement transaction). The remaining gap is failure handling for a paid, non-idempotent call: nothing says whether a failed or retried request is charged again.

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 description coverage is 100%, so the baseline is 3, but the description adds a concrete example input ({"query":"hail storm injury","max":"1"}) that demonstrates string-typed numeric values and real query phrasing beyond what the schema states. It does not add syntax guidance for PubMed-specific operators, which would have pushed this higher.

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 and resource ("PubMed literature search: Searches PubMed (NCBI E-utilities)") and immediately bounds the output ("up to 20 bibliographic records") with the exact field list. No sibling tool covers literature search, and the source and coverage limit (citations only, no abstracts) make the tool's identity unambiguous.

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?

The description supplies clear context for deciding to call it: free upstream source but a paid wrapper, citations-only (no abstracts), and an explicit disclaimer that results are not medical advice. It stops short of naming when to use an alternative or when not to call at all, but the scope and cost statement give an agent enough to judge fit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.