Skip to main content
Glama

X420 agent services

x420_research_pubmed

Read-onlyIdempotent

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. Price: $0.05 USDC per call (x402 on Base). This hosted tool does NOT pay and does NOT return the deliverable: it validates the input and returns payment instructions (pay_to, network, price and the x402 URL to pay at). GET the url; read PAYMENT-REQUIRED from the 402; retry with PAYMENT-SIGNATURE (x402 v2). Or run the local x420-mcp server with your own wallet key to pay automatically. Deliverable once paid: JSON: total, count, results[{pmid, title, authors, journal, pubdate, doi, url}].

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 observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld, but the description adds the crucial behavior the annotations cannot: the hosted tool does NOT return the deliverable, it returns payment instructions, costs $0.05 USDC via x402 on Base, and requires a GET → read PAYMENT-REQUIRED from 402 → retry with PAYMENT-SIGNATURE flow. This is exactly the context an agent needs before calling.

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?

Payment behavior and return fields are front-loaded and useful, but the disclaimer sentence is redundant — 'not medical advice' is immediately followed by a longer near-duplicate list ('Not professional, legal, insurance, engineering, medical, financial or tax advice'), which wastes space without adding value.

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?

For a paid tool with no output schema, the description supplies the deliverable shape (total, count, results[{pmid,title,authors,journal,pubdate,doi,url}] ) and the full payment handshake. An agent has everything needed to call it and interpret the non-deliverable response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so query/max/min_year are already documented in the schema, and the description only restates the 20-record cap implied by 'max'. It adds no syntax or format detail beyond what the schema provides.

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: 'PubMed literature search: Searches PubMed (NCBI E-utilities, free, no key) and returns up to 20 bibliographic records', then enumerates the returned fields. An agent can tell exactly what this produces and distinguish it from the chain/geo/gov siblings.

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?

Sets clear boundaries — 'Citations only, no abstracts; not medical advice' — and explains the two modes (hosted non-paying tool vs. local server with own wallet). It does not name a literature-search alternative, but none appears among the siblings, so there is little to route against.

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