Skip to main content
Glama

ClinX open data: 340B and health centers

One health center's report to HRSA

get_health_center_report
Read-onlyIdempotent

What one health center reported to HRSA in the Uniform Data System for one year, by its key or grant number from find_health_centers. With no table it gives the health center's name and place, the tables of the report with how many lines and cells each has and how many cells carry a mark, and where the full page is. With table (for example Table 3A, patients by age) it gives that table's lines: the line, HRSA's title for it, and for each column the value exactly as HRSA published it. A cell HRSA marked is given as the mark with its meaning (no entry, withheld small count, withheld confidential data) and never as a number. A long table is given in parts: use line, text, offset and limit.

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": {
      "health_center": "<health_center>"
    },
    "name": "get_health_center_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
lineNoOnly this line of the table, as the table lists it (for example L10 or 21a).
textNoOnly the lines whose title holds these words.
yearNoThe reporting year. Default: the latest year held for the health center.
limitNoHow many lines to return (default 40).
tableNoOne table of the report, as the answer without a table lists them: for example Table 3A, Table 5, Table 7, Table 9D, Table HIT, ODE or WFC.
offsetNoHow many lines to skip, for the next part of a long table (default 0).
health_centerYesThe health center's key (for example 010120) or its grant number (for example H80CS00001).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare this a safe, idempotent read, and the description adds genuinely non-obvious behavior: marked cells are returned as the mark with its meaning (no entry, withheld small count, withheld confidential data) and never as a number, which prevents misreading suppressed values as data. It also discloses that long tables are returned in parts, so truncated output is expected rather than a failure.

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 two-mode summary, then the no-table behavior, then the with-table behavior, then the pagination note. Dense but every sentence carries information; the prose is somewhat run-on and could be tightened with clearer separation of the two modes.

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?

No output schema exists, yet the description fully specifies both possible return shapes (report overview with table inventory and counts, or a table's lines with titles and column values) plus pagination signaling and suppressed-cell handling. Nothing essential for a correct call is missing.

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 would be 3; the description earns credit by giving examples of table identifiers (Table 3A = patients by age) and by explaining that line, text, offset and limit exist specifically to page through a long table, which is workflow meaning the schema descriptions state only individually.

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 — what one health center reported to HRSA in the UDS for one year — and distinguishes its two modes precisely: without a table it returns name, place, table inventory with line/cell counts and marked-cell counts plus page location; with a table it returns that table's lines with HRSA's titles and per-column values.

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?

Explains the mode switch clearly (no table = overview of tables; with table = lines of that table) and ties the required health_center key to find_health_centers. It also states the pagination recipe for long tables (line, text, offset, limit). It lacks explicit when-not-to-use guidance or a named sibling to prefer for other report needs.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.