Skip to main content
Glama

ClinX open data: 340B and health centers

One filed 340B report in full

get_filing
Read-onlyIdempotent

One filed report by its filing_id from find_filings: every line as filed with its label, unit and amount; which claim counts are withheld and why (counts of 1 to 5 are never given); how each figure was checked; any discrepancies recorded between figures the report prints; the official file's address, size and SHA-256; and the ClinX page. For a workbook, the cell each figure was read from. One answer holds 100 lines, or up to 150 with limit, and fewer where the lines are long. A longer report is given in parts: the answer says how many lines are left and how to ask for the next part with offset, or for one schedule.

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": {
      "filing_id": "<filing_id>"
    },
    "name": "get_filing"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many lines to return (default 100, at most 150).
offsetNoHow many lines to skip, for the next part of a long report (default 0). The answer names the offset of the next part.
scheduleNoOnly the lines of this schedule, as the line list names it (for example G). The answer lists the schedules the report has.
filing_idYesFor example ri-2025-east-bay-cap.

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?

Beyond the read-only/idempotent annotations it discloses non-obvious behavior: claim counts of 1 to 5 are never returned and withheld counts are explained, discrepancies between printed figures are surfaced, and provenance (official file SHA-256, ClinX page, workbook cell) is included. It also states capacity limits and truncation behavior honestly rather than promising a complete payload.

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?

Despite being dense, the opening clause answers what the tool returns and each subsequent clause adds a distinct capability: line fidelity, withheld counts, verification, provenance, then paging. Nothing is repeated from the title, and the pagination caveat is placed after the content description where it belongs.

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 carries the full burden of describing return values, and it does so thoroughly, including the unusual 100/150-line cap and the partial-response contract. The only soft spot is that the shape of the paging metadata ('the answer says how many lines are left') is described rather than specified, which a schema-less response leaves slightly open.

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 the schema does not carry: limit can yield fewer lines 'where the lines are long', and offset/schedule are the two ways to continue or narrow a part-delivered report, including that the answer names the next offset. That is useful operational semantics beyond the property descriptions.

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 ('One filed report by its filing_id from find_filings') and then enumerates exactly what the record contains: every line with label, unit and amount, withheld claim counts, checks, discrepancies, file address/size/SHA-256, ClinX page, and workbook cell provenance. This is far more precise than the sibling list tools and makes the tool's identity unmistakable.

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?

It anchors the entry point by naming find_filings as the source of the filing_id, which tells an agent it must discover an ID before calling. It also explains the paging route (offset) and the single-schedule route. It does not state when to prefer a sibling such as get_health_center_report instead, so the exclusions are implied rather than explicit.

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.