Skip to main content
Glama

LiveDataLink

by io.github.blackboxfoundry

facility_care_quality

Read-onlyIdempotent

One-call care-quality + provider-identity read for a named US healthcare FACILITY (hospital, nursing home, home-health agency, or hospice). Joins two keyless federal sources: CMS Care Compare (data.cms.gov) for the facility's quality signal - the CMS star rating and, for a hospital, the measure-group highlights (mortality, safety of care, readmission, timely-and-effective care measured better / no different / worse vs national), plus ownership, type, and for a nursing home the health-inspection / staffing / quality-measure star breakdown, certified beds, abuse flag, and fines - and the NPPES NPI Registry for the facility's legal identity (organizational NPI, taxonomy, city/state, active status). Provide a facility name (e.g. 'Cleveland Clinic', 'Mayo Clinic Hospital'); optionally add a 2-letter state to disambiguate and a type (hospital / nursing_home / home_health / hospice) to pin the CMS dataset. When no type is given the tool infers the provider category from the NPPES taxonomy and probes the CMS datasets in order. A leg that fails is noted, not fatal. This is an INFORMATIONAL public-record read, NOT medical advice, a substitute for CMS Care Compare, or an endorsement of any facility.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNoOptional provider category to pin the CMS dataset: 'hospital', 'nursing_home', 'home_health', or 'hospice'. Omit to auto-detect.
stateNoOptional 2-letter state to disambiguate the facility (e.g. 'OH', 'AZ').
facilityYesFacility name to look up (e.g. 'Cleveland Clinic', 'Mayo Clinic Hospital', 'Burns Nursing Home').

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond readOnly/destructive annotations, it discloses source-joining behavior, category inference via NPPES taxonomy, probing order, and that a failed leg is non-fatal. It also flags itself as informational rather than advice or endorsement.

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 summary followed by necessary source and data details; all sentences add information. It is slightly long due to enumerating returned fields, but this compensates for having no output schema.

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?

For a complex multi-source tool with no output schema, the description covers inputs, optional disambiguation, auto-inference, partial failure behavior, and enumerates the expected returned data fields. No critical operational gap remains.

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?

The schema already covers 100% of parameters, and the description adds value by explaining why state/type matter (disambiguation and CMS dataset pinning) and what happens when type is omitted. That is meaningful guidance, though not exhaustive on formats or return types.

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 names a specific operation: a one-call care-quality plus provider-identity read for a named US healthcare facility. It clearly identifies the two federal sources being joined, which separates it from single-source siblings like cms_hospital_search or npi_lookup.

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 explicit input pattern with optional state/type for disambiguation and pinning, plus auto-detection behavior when type is omitted. It also states exclusions (not medical advice, not a substitute for CMS Care Compare), but does not name alternative sibling tools directly.

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

All LiveDataLink toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.3/5.0
Disambiguation2/5

Several tool clusters overlap heavily—company due-diligence and risk tools (counterparty_risk_score, company_trust_check, entity_dossier, issuer_diligence_dossier, resolve_entity, entity_resolve), carrier vetting tools, sanctions screening tools, and recall tools all have subtle boundary distinctions. While descriptions are detailed, an agent navigating 294 tools will frequently struggle to pick the right one.

Naming Consistency3/5

Most tools follow a readable snake_case domain-prefix pattern (fdic_, edgar_, sanctions_, congress_), which helps. However, verb placement is inconsistent—search_available_datasets vs cdc_dataset_query, resolve_entity vs entity_resolve—and synonyms like search, lookup, get, detail, fetch, and status are used interchangeably.

Tool Count1/5

294 tools is an extreme number for a single MCP server, far beyond what an agent can reliably hold in context or select from accurately. The presence of tool-group discovery helpers mitigates but does not solve the fundamental scale problem.

Completeness4/5

The data breadth is genuinely extensive, covering finance, health, legal, real estate, transportation, energy, cyber, education, and many other domains, often with generic query fallbacks. Still, some capabilities are shallow or incomplete—package tracking stops at a link, property tools are demo-only in places, and caselaw coverage is limited—so it is not a fully complete surface.

Resources