Skip to main content
Glama

CounterScript - Drug Price Benchmarks

Look up a US drug's fair cash price

drug_price
Read-onlyIdempotent

Looks up what US pharmacies actually pay to acquire a drug (the CMS NADAC benchmark, per unit, with its date; for a pen, syringe, autoinjector or cartridge priced per mL whose description states what one holds, nadac.per_container gives the price of one, with container, ml and usd, as candidates and biosimilars do; box sizes are not in the data, so no fill estimate follows), a fair cash-price estimate range, FDA generic equivalents, and Medicare negotiated prices where they apply (medicare_negotiated_prices: one entry per year, including a year CMS has announced, with effective_date, price_30d for a 30-day equivalent supply, and per_unit where the NDCs share one). The input is a drug name with optional strength and form. result_type is one of three values. match: one drug, with prices, provenance and honesty notes; a brand-name drug with no generic alternatives listed also carries generic_equivalence, a dated statement of what the FDA Orange Book shows for it, with its ingredient where the file names one (status no_orange_book_match means our match did not pair the product with a listing, which says nothing either way about generics). A brand-name match can also carry cms_generic_price, CMS's NADAC figure for the corresponding generic drug, with its effective date, a fair cash estimate where a fill quantity applies, and the generic's name when exactly one generic in the index has that price, strength and ingredient. A biologic that the FDA Purple Book lists biosimilars to also carries biosimilars (each with proprietary and proper names, interchangeable, marketing_status, file_month, and a NADAC price where one is indexed) and biosimilars_statement; a biosimilar carries reference_product, with the same kinds of fields and a statement. candidates: the query fits several drugs. Up to 12 are listed, each with its description and price hint, in this order: the drug named on its own first, then combinations with other drugs, then longer names that hold the word (esomeprazole for omeprazole); generics before brands, then alphabetical with doses in number order (2.5 mg before 10 mg), within each. A number in the query matches only that whole number, so a query for 5 mg does not list 2.5 mg or 15 mg; within each group, drugs that hold every query word whole come first. candidates_total gives how many drugs matched; when that is more than 12, message says the list was cut, and adding a strength or form narrows it. A query equal to one candidate's description returns that drug as a match. no_match: the index has no drug matching the query; this does not mean the drug lacks a fair price, since NADAC covers only drugs with enough pharmacy survey data. did_you_mean, where present, lists drug names to search next, and did_you_mean_basis gives the reason: spelling (the name the query spells, apart from spaces and punctuation, without a dose the index lacks, or names beginning with it; a number typed with no unit is part of the name unless the words before it are a drug name, so vanacof 2 does not get vanacof dm, and stays part of it, whatever the basis, where catalog names put a number of their own after those words or an FDA label name holds it, so vagistat 3, a miconazole kit, does not get tioconazole of VAGISTAT-1, nor sore throat 911, a potassium lotion, the phenol SORE THROAT; for a trade name that is its only active ingredient plus more words, such as theophylline-sr, that ingredient), same_ingredient (the index has no drug under the ingredient name in the query, and the names are priced brands whose only active ingredient in the FDA Orange Book is that ingredient, or, for a biologic, priced brands whose proper (ingredient) name in the FDA Purple Book is that name, such as trulicity for dulaglutide; message adds a sentence naming the catalog and its file; store brands of the ingredient may still be priced under their own names) or generic_name (the index has no drug under the brand name in the query; the one name is that brand's active ingredient, or its ingredients joined by "and", in the FDA Orange Book, such as tamsulosin hydrochloride for flomax, and searching it lists the priced products with it; message adds a sentence naming the file; the name is an ingredient, not a statement that any product is a substitute; a pack name a maker's label gives a brand counts as that brand, so z-pak, Pfizer's pack of Zithromax 250 mg tablets, gets azithromycin; a name current FDA labels use for other drugs gets none, so midol, ibuprofen in the Orange Book but acetaminophen, caffeine and pyrilamine on its label, gets no hint, nor does allay, a discontinued hydrocodone combination whose only current label is a sunscreen; and leading words of a trade name that begin a priced name of another drug get none, so 8 hour, of the discontinued aspirin 8-HOUR BAYER, is not aspirin, since the index prices 8 HOUR ACETAMINOPHEN ER; and leading words that are no name of a drug get none: three letters or fewer, such as cap of CAP-PROFEN (epi, short for epinephrine, aside), and everyday words such as extended or junior, of EXTENDED PHENYTOIN SODIUM and JUNIOR STRENGTH ADVIL). A query that finds nothing as typed is read again: with a hyphen between a number and a word as a space, so 8-hour finds what 8 hour finds; with a bracketed part's brackets dropped, then with the part left out, such as eliquis for "eliquis (apixaban)"; and as a label writes a drug name, so a salt finds NADAC's short form or a description without it (sertraline hydrochloride finds SERTRALINE HCL) and amoxicillin and clavulanate potassium finds AMOX-CLAV. A name the FDA Orange Book or Purple Book lists that no description holds as whole words beginning its first or second word finds nothing, so ranexa gets its ingredient rather than TRANEXAMIC ACID. No name is guessed from a misspelling: did_you_mean holds no name with letters the query lacks or changes (lipiter gets none), since a real name a letter or two from another is often a different drug (afrin is not errin). A spelling hint is a search aid, not an equivalent medicine. Every result also carries freshness, one entry per source (nadac, orangebook, mfp, purplebook) giving as_of, the publisher's date on the file in use (for purplebook, which FDA dates by month, the first day of that month); checked, the date of our newest successful fetch of that source; expected, the publishing cadence (weekly, monthly or irregular); and stale, which is true when the NADAC file is more than 10 days old, the Orange Book file more than 45 days old or the month of the Purple Book file ended more than 60 days ago, or when our newest attempt to fetch that source failed (last_attempt_failed then gives that attempt's date, and the file in use is the newest good one we hold), and then statement says so in plain words. For mfp, whose updates are irregular, stale is true only after a failed fetch. A source we have not fetched yet has no as_of or checked.

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": "drug_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesDrug name with optional strength/form, e.g. "atorvastatin 20 mg" or "eliquis 5 mg tablet". Generic (ingredient) names match best.

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 readOnly, idempotent, non-destructive and closed-world, so the description's job is to add beyond that — and it does substantially: it discloses that no_match means the index lacks survey data rather than the drug lacking a price, gives the 12-candidate cap, the exact candidate ordering rules, and per-source staleness thresholds (10/45/60 days, failed-fetch fallback). It stops short of describing response size or latency, which keeps it off a 5.

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

Conciseness1/5

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

A single multi-hundred-word sentence interrupted by a ~90-word parenthetical about per-mL container pricing, with nested quotation marks, escaped quotes and case-by-case anecdotes (midol, allay, 8 hour, vanacof 2) packed inline. The critical output contract — the three result_type values — is buried mid-paragraph rather than front-loaded, and the volume is wildly disproportionate to a one-parameter read tool.

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?

With no output schema, the description must carry the return contract, and it does: all three result_type branches, the fields each branch carries (nadac.per_container, generic_equivalence statuses, biosimilars, cms_generic_price, did_you_mean_basis, freshness with as_of/checked/expected/stale), and their caveats. Nothing needed to interpret a response correctly is missing.

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% with a single parameter, so the baseline is 3. The description earns above that by documenting parsing behavior the schema cannot: a number matches only that whole number (5 mg excludes 2.5 and 15 mg), a hyphen between number and word is retried as a space, bracketed parts are dropped, and salt forms are normalized (sertraline hydrochloride -> SERTRALINE HCL).

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?

The opening clause names a specific resource and scope: what US pharmacies actually pay to acquire a drug, on the CMS NADAC benchmark, plus a fair cash-price range, FDA generic equivalents and Medicare negotiated prices. An agent knows exactly what comes back without opening the schema.

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?

No siblings exist, so there is no alternative to route to. The description does state the input shape ('a drug name with optional strength and form') and warns that adding a strength or form narrows a truncated candidate list, which is genuine usage guidance, but there is no explicit when-not-to-use or precondition framing.

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