Skip to main content
Glama
mymedi-ai-mcp-server

mymedi-ai-mcp-server

by MyMedi-AI

DMEPOS order documentation audit (SWO, F2F/WOPD, prior auth)

compliance_audit
Read-only

Audit one DMEPOS order's documentation against Original Medicare requirements for its HCPCS code and date of service, returning pass/fail with citations for each requirement.

Instructions

Audit one DMEPOS order's documentation against the Original Medicare requirements that apply to its HCPCS code on the date of service: the standard written order (SWO) elements (42 CFR 410.38(d)(1)(i)); for items on the current CMS Required Face-to-Face Encounter & Written Order Prior to Delivery List, a face-to-face encounter within the 6 months before the order and the written order before delivery, otherwise the written order before the claim; and for items on the current CMS Required Prior Authorization List, an affirmed decision before delivery. Some items are phased in by state: without a state such an order is refused (refunded) unless an affirmed decision is reported. A code the HCPCS set does not hold, one not valid on the date of service, or one the CMS DMEPOS Jurisdiction List bills to the A/B MAC (Part B) rather than a DME MAC, or a discontinued code that list does not show, is refused (refunded); for a code under joint jurisdiction the answer gives CMS's wording of when the A/B MAC takes it. Each fact is a true/false flag; no names, identifiers, signatures or other values are taken. Each requirement comes back pass or fail with its citation; a fact not reported fails, and any failed requirement fails the order (result: fail). It checks the facts reported, not the documents themselves. Not checked: LCD coverage criteria and medical-necessity documentation, proof of delivery and billing modifiers. Costs 250 credits per call.

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": {
      "data": "<data>"
    },
    "name": "compliance_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataYesThe order: its HCPCS code, date of service and state, and true/false facts about its documentation
auditTypeNoOptional: "dme_order", the only audit (the default)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.7.9
    • changedInput schema / properties / auditType / description
      Previous value: -"Type of audit (default: general)"New value: +"Optional: \"dme_order\", the only audit (the default)"
    • changedInput schema / properties / auditType / enum
      Previous value: -[
      -  "general",
      -  "hipaa"
      -]New value: +[
      +  "dme_order"
      +]
    • changedInput schema / properties / data / additionalProperties
      Previous value: -{}New value: +false
    • changedInput schema / properties / data / description
      Previous value: -"Data to audit for compliance issues"New value: +"The order: its HCPCS code, date of service and state, and true/false facts about its documentation"
    • addedInput schema / properties / data / properties
      Added value: +{
      +  "code": {
      +    "description": "HCPCS Level II code of the ordered item (e.g., \"K0823\")",
      +    "maxLength": 500,
      +    "type": "string"
      +  },
      +  "dateOfService": {
      +    "description": "Date of service (for DME, the delivery date), YYYY-MM-DD",
      +    "maxLength": 10,
      +    "type": "string"
      +  },
      +  "faceToFaceWithin6Months": {
      +    "description": "F2F/WOPD items: a face-to-face encounter with the treating practitioner within the 6 months before the order date",
      +    "type": "boolean"
      +  },
      +  "orderBeforeClaim": {
      +    "description": "Other items: the written order reached the supplier before the claim is submitted",
      +    "type": "boolean"
      +  },
      +  "orderBeforeDelivery": {
      +    "description": "F2F/WOPD items: the written order reached the supplier before delivery",
      +    "type": "boolean"
      +  },
      +  "priorAuthorization": {
      +    "description": "Prior-authorization items: \"affirmed\" when an affirmed decision was received before delivery",
      +    "enum": [
      +      "affirmed",
      +      "non_affirmed",
      +      "pending",
      +      "not_requested"
      +    ],
      +    "type": "string"
      +  },
      +  "state": {
      +    "description": "2-letter US state or territory; needed for items phased in by state",
      +    "enum": [
      +      "AL",
      +      "AK",
      +      "AZ",
      +      "AR",
      +      "CA",
      +      "CO",
      +      "CT",
      +      "DE",
      +      "FL",
      +      "GA",
      +      "HI",
      +      "ID",
      +      "IL",
      +      "IN",
      +      "IA",
      +      "KS",
      +      "KY",
      +      "LA",
      +      "ME",
      +      "MD",
      +      "MA",
      +      "MI",
      +      "MN",
      +      "MS",
      +      "MO",
      +      "MT",
      +      "NE",
      +      "NV",
      +      "NH",
      +      "NJ",
      +      "NM",
      +      "NY",
      +      "NC",
      +      "ND",
      +      "OH",
      +      "OK",
      +      "OR",
      +      "PA",
      +      "RI",
      +      "SC",
      +      "SD",
      +      "TN",
      +      "TX",
      +      "UT",
      +      "VT",
      +      "VA",
      +      "WA",
      +      "WV",
      +      "WI",
      +      "WY",
      +      "DC",
      +      "PR",
      +      "VI",
      +      "GU",
      +      "AS",
      +      "MP"
      +    ],
      +    "type": "string"
      +  },
      +  "swo": {
      +    "additionalProperties": false,
      +    "description": "Standard written order elements: true when on the order (quantity: also when none applies), false when missing — never the values",
      +    "properties": {
      +      "beneficiaryName": {
      +        "description": "Beneficiary name or Medicare Beneficiary Identifier (MBI)",
      +        "type": "boolean"
      +      },
      +      "itemDescription": {
      +        "description": "General description of the item",
      +        "type": "boolean"
      +      },
      +      "orderDate": {
      +        "description": "Order date",
      +        "type": "boolean"
      +      },
      +      "practitionerName": {
      +        "description": "Treating practitioner name or NPI",
      +        "type": "boolean"
      +      },
      +      "practitionerSignature": {
      +        "description": "Treating practitioner signature",
      +        "type": "boolean"
      +      },
      +      "quantity": {
      +        "description": "Quantity to be dispensed, if applicable",
      +        "type": "boolean"
      +      }
      +    },
      +    "type": "object"
      +  }
      +}
    • addedInput schema / properties / data / required
      Added value: +[
      +  "code",
      +  "dateOfService"
      +]
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: 250 credits per call, refund-on-refusal behavior for phased-in states and non-billable/discontinued codes, fail-closed semantics ('a fact not reported fails'), and confirmation that it evaluates reported facts rather than documents. These are operationally decisive details an agent cannot get from readOnlyHint/openWorldHint alone.

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 core verb and resource, and the dense clauses each carry distinct information (refusal cases, phase-in, cost, exclusions). The single long paragraph and nested parentheticals make it heavier than ideal, but little is genuinely expendable.

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?

Covers inputs, refusal paths, phase-in-by-state caveat, cost, and result semantics (per-requirement pass/fail with citation, overall result fail). With no output schema, the description nonetheless explains what comes back well enough for an agent to interpret the response.

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%, so the baseline is 3, but the description adds real meaning: it explains that facts are true/false flags carrying no names, MBIs, signatures or values, and that an unreported fact is treated as a failure. That changes how an agent should populate and omit fields, which the schema alone does not convey.

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 (audit one DMEPOS order's documentation) scoped to Original Medicare rules keyed off HCPCS code and date of service. It is clearly distinguishable from siblings such as pa_required_check or order_readiness_checklist because it self-describes as a citation-backed pass/fail audit of reported facts.

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 concrete applicability conditions (which items require F2F/WOPD or prior auth, when a state is required, which codes get refused) and an explicit exclusion list (LCD coverage, medical necessity, proof of delivery, modifiers). It does not name an alternative sibling tool to use instead when the order falls outside scope, which keeps it below a 5.

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