Skip to main content
Glama

Epstein Search Documents

epstein_search_documents
Read-onlyIdempotent

Full-text search across the House Oversight Committee documents from the Jeffrey Epstein investigation, transcribed interviews, subpoenas and letters the committee published as PDFs. Returns the matching page with a snippet, the document title and the committee URL, so every result can be checked at source. Use it to find what a named witness said under questioning, which institutions were subpoenaed, or where a topic appears in the record.

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": {
      "query": "non-prosecution agreement"
    },
    "name": "epstein_search_documents"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax matching pages, default 10, max 50.
queryYesWords to find in the document text, e.g. "Metropolitan Correctional Center" or "non-prosecution agreement".
doc_typeNoRestrict to one kind of document.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds genuinely new context: results are page-level with a snippet, document title and committee URL, making every hit verifiable at source. It omits ranking/ordering behavior and any pagination beyond what the schema's limit field states.

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?

Three tight sentences: corpus scope first, then return shape/provenance, then usage examples. No filler; the only slight redundancy is that the usage sentence restates the subject matter already established in sentence one.

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?

There is no output schema, so the description correctly carries the return-shape burden by naming snippet, title and URL. With all three parameters documented in the schema and safety traits in annotations, an agent has what it needs to invoke this search correctly; only result ordering and page-count semantics remain unstated.

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 coverage is 100%, including a documented default/max for limit and an enumerated doc_type, so the baseline of 3 applies. The description's mention of full-text matching and doc types adds little beyond the schema's own examples and field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Full-text search across the House Oversight Committee documents from the Jeffrey Epstein investigation') and scopes the corpus precisely (transcribed interviews, subpoenas, letters published as PDFs). It does not explicitly name its siblings (epstein_list_documents, epstein_get_document), so the distinction from browsing or fetching a whole document is left implicit.

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 concrete usage contexts — finding what a named witness said, which institutions were subpoenaed, or where a topic appears. It stops short of explicit when-not-to-use guidance or naming an alternative tool for full-document retrieval or listing the document inventory.

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.