Oig Self Disclosure Settlements

Oig Sdp Recent

oig_sdp_recent

Read-onlyIdempotent

The most recent HHS-OIG Self-Disclosure Protocol settlements — providers (and, separately, grantees/contractors) who voluntarily self-disclosed conduct to OIG and agreed to pay a Civil Monetary Penalties Law settlement to resolve it. Different from a Corporate Integrity Agreement (mcps/oig-corporate-integrity): most SDP settlements carry no ongoing compliance obligation, just a one-time payment. Returns totals first — the matching count, the corpus totals by program, and the approximate dollar sum of the returned page (headline figures, sometimes rounded) — then the settlements themselves, newest first: provider, date, headline amount, allegation and a detail-page link. Sourced from HHS-OIG, keyless.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "limit": 5,
      "program": "provider"
    },
    "name": "oig_sdp_recent"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max rows to return (default 25, max 100).
`offset`	No	Rows to skip, for paging (default 0).
`program`	No	"provider" for Provider Self-Disclosure Protocol settlements (the large majority, ~1,057), "grant" for Grant and Contractor Self-Disclosure Program settlements (~17), or "all" (default).

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior it does not repeat: keyless sourcing from HHS-OIG, totals-first response shape (count, corpus totals by program, approximate page dollar sum), newest-first ordering, and the caveat that headline amounts are sometimes rounded. That rounding/approximation note is exactly the kind of output caveat an agent needs.

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 identity of the dataset and efficient overall, though the middle sentence packs several ideas (CIA contrast, compliance-obligation nuance) and the parenthetical heap makes it denser than it needs to be. Nothing is wasted, but the flow is slightly heavy.

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?

With no output schema, the description takes on the burden of describing the return payload — totals block followed by settlement rows with provider, date, amount, allegation, and detail link — and does so fully. An agent has everything needed to call it and interpret the response.

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 description coverage is 100%, and the enum values are already fully explained in the schema (including the ~1,057 / ~17 counts), so the description adds little parameter-level meaning beyond restating the provider vs. grant distinction. Baseline 3 is appropriate when the schema carries the load.

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 verb+resource (most recent HHS-OIG Self-Disclosure Protocol settlements) and immediately scopes what counts: providers and, separately, grantees/contractors who self-disclosed and paid a CMPL settlement. It also distinguishes the record type from a Corporate Integrity Agreement, so an agent can tell what corpus it is querying before opening the schema.

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 gives clear selection context — it is the 'newest first' feed of SDP settlements and explicitly not the CIA material (mcps/oig-corporate-integrity). What is missing is explicit routing against its closest sibling, oig_sdp_check (presumably a single-entity lookup); the agent must infer that this is the browse/list tool rather than the check tool.

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

All Oig Self Disclosure Settlements tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.