Skip to main content
Glama
jamesrosing

tebra-mcp-server

by jamesrosing

Get Transactions

tebra_get_transactions
Read-only

Fetch Tebra financial transactions using filters for date range, type, payer, procedure code, and practice, returning details on patient, claim, and insurance.

Instructions

Get financial transactions from Tebra with optional date range, type, payer, procedure code, and practice filters. Returns transaction details with patient, claim, and insurance info.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fieldsNoOptional list of result fields to return (dotted paths for nested values, e.g. "cases.policies.companyName"). Omit for the default field set. Request only the fields you need — results contain protected health information.
payerTypeNoOptional payer type filter
practiceNameNoOptional practice name filter
procedureCodeNoOptional CPT/procedure code filter
toPostingDateNoOptional end posting date filter (ISO 8601)
toServiceDateNoOptional end service date filter (ISO 8601)
insuranceOrderNoOptional insurance order filter (e.g. Primary, Secondary)
fromPostingDateNoOptional start posting date filter (ISO 8601)
fromServiceDateNoOptional start service date filter (ISO 8601)
transactionTypeNoOptional transaction type filter (sent as WSDL Type member)
toTransactionDateNoOptional end transaction date filter (ISO 8601)
toLastModifiedDateNoOptional end last-modified date filter (ISO 8601)
fromTransactionDateNoOptional start transaction date filter (ISO 8601)
fromLastModifiedDateNoOptional start last-modified date filter (ISO 8601)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.6.0
    • addedInput schema / properties / fields
      Added value: +{
      +  "description": "Optional list of result fields to return (dotted paths for nested values, e.g. \"cases.policies.companyName\"). Omit for the default field set. Request only the fields you need — results contain protected health information.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / fromLastModifiedDate
      Added value: +{
      +  "description": "Optional start last-modified date filter (ISO 8601)",
      +  "type": "string"
      +}
    • addedInput schema / properties / insuranceOrder
      Added value: +{
      +  "description": "Optional insurance order filter (e.g. Primary, Secondary)",
      +  "type": "string"
      +}
    • addedInput schema / properties / toLastModifiedDate
      Added value: +{
      +  "description": "Optional end last-modified date filter (ISO 8601)",
      +  "type": "string"
      +}
    • changedInput schema / properties / transactionType / description
      Previous value: -"Optional transaction type filter"New value: +"Optional transaction type filter (sent as WSDL Type member)"
  2. First observedv0.2.5

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint, so the description only needs to add context beyond those. It adds the return shape (patient, claim, insurance) but does not disclose pagination, result volume, or PHI handling beyond what appears in the fields parameter schema. No contradictions with 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?

The description is two short sentences with no filler. The core action and filter scope are front-loaded, and the return summary is included without repeating schema-level parameter details.

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?

With no output schema, the description correctly provides a high-level return summary. Combined with fully documented parameters and safety-carrying annotations, it is largely complete for a retrieval tool, though it could optionally mention pagination or large-result-set behavior for a financial transaction query.

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 description coverage is 100% and all 14 parameters have individual descriptions. The tool description only restates filter categories (date range, type, payer, procedure code, practice) and adds no syntax or semantic detail beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly names a concrete resource (financial transactions from Tebra) and a retrieval verb, and summarizes the returned data (patient, claim, insurance). It is clear what the tool does, but it does not explicitly distinguish it from financial siblings like tebra_get_charges or tebra_get_payments.

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?

The description implies usage when the agent needs transaction-level financial records with optional filters, but it provides no explicit when-to-use/when-not-to-use guidance and names no alternatives. Given the sibling list contains other financial record tools, the routing is implied rather than stated.

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