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

mymedi-ai-mcp-server

by MyMedi-AI

AI-enriched provider intelligence (NPI)

provider_enrich
Read-only

Look up a provider by NPI in the CMS NPPES registry and add a labeled LLM estimate of specialty demand, network gaps, and referral categories.

Instructions

Look up a provider by NPI in the CMS NPPES registry (name, credential, primary and other taxonomies, practice address, enumeration date) and add an LLM-generated estimate, labelled as such, of specialty demand, network gaps and referral categories for that type of provider. The model is given the provider type — specialty, taxonomy, credential, state, entity type and enumeration date — never the name or NPI. Not a CMS or quality measure. A failed call (unknown NPI, model unavailable) is refunded.

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": {
      "npi": "<npi>"
    },
    "name": "provider_enrich"
  }
}

Input Schema

NameRequiredDescriptionDefault
npiYes10-digit NPI number

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.7.9
    • addedInput schema / properties / npi / maxLength
      Added value: +500
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover read-only, non-destructive and open-world, yet the description goes further: the LLM output is labelled as an estimate, the model receives only provider type (never name or NPI), and failed calls are refunded. It does not explain why idempotentHint=false (presumably non-deterministic LLM output) or mention cost/latency, which would have completed the picture.

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 lookup, then the enrichment, then constraints (privacy, disclaimer, refund). Dense but nearly every clause carries information; the absence of headings or line separation makes the caveats easy to skim past.

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?

For a 1-parameter read-only tool with no output schema, it names the registry fields returned and the three enrichment outputs, plus failure behavior. Only the shape of the returned estimate and its cost remain unspecified.

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% and the single npi parameter is already documented as a '10-digit NPI number'. The description adds only that the number resolves against the NPPES registry, no extra format or validation guidance — baseline 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?

States a specific verb+resource (look up a provider by NPI in the CMS NPPES registry) and enumerates the fields returned plus the AI-generated additions (specialty demand, network gaps, referral categories). It does not name or differentiate against the obvious sibling provider_search, so an agent must infer which to pick for name-based lookups.

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 NPI-keyed framing plus 'Not a CMS or quality measure' implies when it applies, but there is no explicit when-to-use/when-not or routing to provider_search for non-NPI searches. Usage is inferable rather than stated.

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