Medicaid Intelligence

Medicaid Drug State Market

medicaid_drug_state_market

Read-onlyIdempotent

Which states spend the most on a drug — one year of Medicaid reimbursement broken down by state, keeping fee-for-service and managed care separate. Ask by NAME ("Ozempic") or by an exact 11-digit NDC. Suppressed rows remain unavailable and totals are gross pharmacy reimbursement before rebates.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "drug": "Ozempic",
      "year": 2025
    },
    "name": "medicaid_drug_state_market"
  }
}

Input Schema

Name	Required	Description
`ndc`	No	Exact 11-digit National Drug Code, hyphenated or not, e.g. "00002-1433-80". Optional — give this OR drug. An NDC narrows to one package size.
`drug`	No	Drug name as it appears on the package, e.g. "Ozempic" or "Humira" — matched against the Medicaid product list, aggregating every package size. A generic ingredient is expanded to its NDCs automatically when Medicaid lists it only under brands.
`year`	No	Calendar year 2020-2026. Defaults to the most recent year with data.

Output Schema

Name	Required	Description	Default
`total`	Yes
`source`	Yes
`states`	Yes
`returned`	Yes
`interpretation`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedAug 12, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "ndc": "00002143380",
-    "year": 2025
-  }
-]New value: +[
+  {
+    "drug": "Ozempic",
+    "year": 2025
+  },
+  {
+    "ndc": "00002143380",
+    "year": 2025
+  }
+]

addedInput schema / properties / drug

Added value: +{
+  "description": "Drug name as it appears on the package, e.g. \"Ozempic\" or \"Humira\" — matched against the Medicaid product list, aggregating every package size. A generic ingredient is expanded to its NDCs automatically when Medicaid lists it only under brands.",
+  "type": "string"
+}

changedInput schema / properties / ndc / description

Previous value: -"Exact 11-digit National Drug Code, hyphenated or not, e.g. \"00002-1433-80\" or \"00002143380\". Resolve a brand or ingredient name to an NDC first with openfda_drug_label or rxnorm."New value: +"Exact 11-digit National Drug Code, hyphenated or not, e.g. \"00002-1433-80\". Optional — give this OR drug. An NDC narrows to one package size."

changedInput schema / required

Previous value: -[
-  "ndc"
-]New value: +[]

First observedAug 3, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable context beyond annotations: suppressed rows remain unavailable, totals are gross reimbursement before rebates, and FFS vs managed care are separated. This enhances understanding of the data and its limitations without contradicting the annotations.

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?

Three well-structured sentences: first states the core question and output breakdown, second explains query by name or NDC, third covers data caveats (suppression, rebates, type of reimbursement). Every sentence serves a distinct purpose with no filler.

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?

Given the presence of an output schema and annotations, the description sufficiently covers the tool's scope and key caveats. It explains state-level breakdown, FFS vs managed care, the definition of 'spend' (gross before rebates), and suppression behavior. Minor missing context like result ordering or pagination is likely handled by the output schema. This is complete for the tool's complexity.

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?

The schema descriptions for all three parameters are thorough (100% coverage), including examples and the OR relationship between drug and NDC. The description reiterates the name-or-NDC choice but doesn't add significant semantic meaning beyond the schema. 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?

The description clearly states that the tool breaks down Medicaid drug reimbursement by state for one year, with fee-for-service and managed care separated. This is a specific verb+resource that distinguishes it from siblings like medicaid_drug_trend (which likely shows time trends) and medicaid_drug_utilization (usage volume).

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 provides a clear use case ('Which states spend the most on a drug') and clarifies how to query (by name or exact NDC). It does not explicitly name alternative tools or when-not-to-use, but the state-market scope implicitly differentiates it from trend or utilization tools. Context is clear, though exclusions are not stated.

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

All Medicaid Intelligence 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.