SiteCheck Web Intel

NHS England primary-care prescribing for a drug: items

search_openprescribing

Read-only

NHS England primary-care prescribing for a drug (official NHSBSA English Prescribing Dataset, monthly, ~2 months behind; the raw data behind OpenPrescribing.net): items, actual cost (GBP) and quantity, grouped by region, ICB, GP practice or product presentation, largest first. Match on BNF chemical substance or presentation name. Open Government Licence, no key. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

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": {
      "drug": "<drug>"
    },
    "name": "search_openprescribing"
  }
}

Input Schema

Name	Required	Description
`area`	No	Only rows whose ICB or region name contains this text, e.g. manchester (optional)
`drug`	Yes	Drug name contained in the BNF chemical substance or presentation name, e.g. metformin, atorvastatin, semaglutide (2 to 60 characters)
`limit`	No	How many groups, 1 to 100 (default 20)
`month`	No	Month as YYYYMM, e.g. 202608 (default latest published)
`groupBy`	No	region, icb, practice or presentation (default icb)

Output Schema

Name	Required	Description	Default
`area`	No
`drug`	No
`count`	No
`month`	No
`groups`	No
`source`	No
`groupBy`	No
`checkedAt`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: discloses data provenance, monthly cadence with ~2-month publication lag, Open Government Licence with no API key, and the exact billing model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, failures not charged). Cost and payment mechanics are critical pre-invocation facts an agent cannot infer from any structured field, and nothing contradicts readOnlyHint=true.

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 resource and dataset before the parenthetical provenance, and every clause (lag, licence, pricing) carries information the agent needs. It is dense as a single long sentence with stacked parentheses, which slightly hurts scannability, but there is no filler.

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?

An output schema exists, so return values need not be described. For a five-parameter read tool, the description covers source, freshness, matching semantics, grouping granularity, sort order, licensing, and cost — everything needed to decide and call correctly.

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 the schema already documents every parameter including defaults and examples. The description adds some genuine meaning beyond it — that matching is a substring on BNF chemical substance or presentation name, and that results are ordered largest first — but not enough to be a strong differentiator. Baseline 3 is appropriate.

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: NHS England primary-care prescribing for a drug, with the metrics returned (items, actual cost in GBP, quantity), the grouping levels (region, ICB, GP practice, product presentation), and sort order (largest first). The named dataset (NHSBSA English Prescribing Dataset) and upstream site (OpenPrescribing.net) make it unmistakable against the news/search 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?

Gives clear context for when this applies — querying official monthly English prescribing data, matched on BNF chemical substance or presentation name — and the ~2-month lag tells the agent not to use it for current-month figures. It stops short of explicit when-not-to-use guidance or naming alternatives (e.g., practice-level vs presentation-level tradeoffs), so it is strong but not exhaustive.

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

All SiteCheck Web Intel tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?