Skip to main content
Glama

Cms Open Payments

by io.github.pipeworx-io

Open Payments Top Companies

open_payments_top_companies
Read-onlyIdempotent

Rank the drug and device manufacturers that paid US physicians and teaching hospitals the most in a program year — the "who spends the most on doctors" question. Returns each company with its total US dollars, payment count and how many distinct recipients it reached, ordered by spend. CMS publishes no aggregate and its live API cannot group over the 14-million-row payment table, so this reads a summary computed offline; the response states the program year and when the summary was refreshed. Payments are disclosures of transfers of value, not evidence of wrongdoing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoCompanies to return, 1-200 (default 25).
companyNoOptional: one company, to get its total rather than the ranking. Matched case-insensitively.
program_yearNoProgram year, e.g. 2025. Defaults to the most recent year loaded — the response always says which.

Schema Changelog

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

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "limit": 3
+  },
+  {
+    "company": "Pfizer",
+    "program_year": 2025
+  }
+]
  2. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds behavioral context: the tool reads a pre-computed offline summary (not live), discloses staleness risk, and clarifies that payments are disclosures not evidence of wrongdoing. This goes beyond annotations.

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?

Description is informative yet compact, front-loading the purpose and constraints. The additional context on CMS limitations and payment interpretation is valuable, though the sentence on CMS could be slightly more concise. Still, no wasted words.

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?

Given 3 optional parameters, no output schema, and comprehensive annotations, the description covers what the tool does, why needed, and response contents. Minor gap: does not specify if it requires any particular authentication or rate limits, but these are likely covered elsewhere.

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 covers 100% of parameters with descriptions (limit, company, program_year). The description adds meaning by explaining why parameters exist (e.g., 'limit' for ranking, 'company' for querying a specific company) and clarifying defaults and behavior (case-insensitive match). This slightly elevates above baseline 3.

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 clearly states the tool ranks drug/device manufacturers by payments to US physicians and teaching hospitals, specifying verb ('rank'), resource ('drug and device manufacturers'), and context ('program year'). It distinguishes itself from siblings like open_payments_company by focusing on top companies aggregated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly explains why to use this tool (CMS publishes no aggregate, live API cannot group 14 million rows) and when not to (if needing per-company details, use open_payments_company). It provides clear context for the offline computed summary.

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

All Cms Open Payments 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

A3.6/5.0
Disambiguation3/5

Tools like ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are very similar, causing potential confusion. The open_payments_* tools are clearly differentiated, but the mix of generic Pipeworx tools with domain-specific ones creates overlapping purposes.

Naming Consistency2/5

Tool names mix conventions: some use snake_case (ask_pipeworx, open_payments_company), while others use less consistent patterns (deep_research, generate_llms_txt). The open_payments_* tools have a consistent prefix, but the overall set lacks a unified naming scheme.

Tool Count2/5

With 41 tools, the server is heavily overloaded for a domain focused on CMS Open Payments. The majority of tools are general-purpose Pipeworx tools unrelated to the server's name, making the count feel excessive and unfocused.

Completeness3/5

The open_payments_* tools cover the CMS Open Payments domain well (search, company, physician, history, etc.). However, the inclusion of many unrelated Pipeworx tools means the server as a whole is not cohesive, and the completeness of the named domain is overshadowed.

Resources