Skip to main content
Glama

Epstein Flight Log Search

epstein_flight_log_search
Read-onlyIdempotent

Structured search over Epstein's pilot flight logbook (Government Exhibit 662-RR, USA v. Ghislaine Maxwell, 20-cr-330, S.D.N.Y.), date, aircraft, tail number, route and the pilot's own passenger/remarks entry for each leg. Passenger initials and names are returned EXACTLY as the pilot wrote them ('JE, GM, SK'), never resolved to a full identity, per design decision C on this build. A token the transcriber could read but not confirm carries a trailing '[?]'; a wholly unreadable token is '[illegible]', neither stands in for a guessed identity. Only 397 of an estimated 3,000+ logged legs are ingested (23 of 118 exhibit pages, spanning 1991-2005) because the rest requires further page-by-page visual transcription, call epstein_flight_log_search with no filters to see exactly which pages are covered before concluding an absence. Use it to find who is logged on a given tail number, route or date range, or to search the remarks text for a name or initials.

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": {
      "tail_number": "N908JE"
    },
    "name": "epstein_flight_log_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoArrival identifier as printed, e.g. "PBI".
fromNoDeparture identifier as printed, e.g. "TEB".
limitNoMax rows, default 20, max 100.
date_toNoLatest flight date, YYYY-MM-DD.
date_fromNoEarliest flight date, YYYY-MM-DD.
passengerNoSubstring to find in the remarks/passenger entry, e.g. "GM" or "Clinton". Case-insensitive.
tail_numberNoAircraft registration as printed, e.g. "N908JE".

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 readOnly/idempotent annotations, it discloses return semantics the agent could not otherwise know: passenger names are returned exactly as written and never resolved to identities, with '[?]' and '[illegible]' conventions for uncertain tokens. It also states a hard coverage limitation (397 of 3,000+ legs, 23 of 118 pages, 1991-2005), which directly affects how results should be interpreted.

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 resource and provenance, then behavior, then usage. Dense but each clause carries information; the parenthetical legal citation and page-count detail are slightly verbose but materially support the coverage caveat.

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?

For a read-only, filter-based search with no output schema, the description covers what is searchable, how results are rendered, transcription uncertainty markers, and the dataset's incompleteness — everything an agent needs to call it and to avoid false conclusions from missing rows.

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; the description adds meaning by explaining that the passenger filter matches the pilot's own remarks entry as transcribed, which determines what query strings will and will not hit. It does not add syntax detail for the route or date parameters beyond the schema.

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 — 'structured search over Epstein's pilot flight logbook' — with the exact exhibit provenance (662-RR, 20-cr-330) and the fields searchable (date, aircraft, tail number, route, remarks). It is clearly a fielded/logbook search tool, distinguishable from document-level siblings.

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?

Gives explicit use cases ('find who is logged on a given tail number, route or date range, or to search the remarks text') plus a critical negative guidance: call with no filters to check coverage before concluding an absence. It does not name a specific alternative tool for full-text document search, which keeps it from a 5.

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.