Skip to main content
Glama

Fara

by io.github.pipeworx-io

Search Registrants

search_registrants
Read-onlyIdempotent

Search FARA registrants — US agents registered to represent FOREIGN principals (foreign governments, parties, businesses) for lobbying/influence inside the US. FARA has no server-side search, so this fetches the bulk active-registrant dump (~556 rows) once and filters CLIENT-SIDE by a name substring (case-insensitive); results are capped. Set status="terminated" to search the much larger terminated dump (~6,500 rows, ~1.4MB fetched once). Returns each registrant's name, registration_number (use it with list_foreign_principals / get_registrant_documents), address and registration_date. Keyless.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoCase-insensitive substring matched against the registrant name + business name, e.g. "scoyoc", "global", "BGR". Omit to return the first page of all registrants.
limitNoMax rows to return (default 25, hard cap 100).
statusNoWhich registrant dump to search. Default "active".

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds critical behavioral details: client-side filtering, data fetched once, row counts and sizes, result capping. Fully transparent.

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?

Four sentences, front-loaded with purpose and key mechanics. No fluff; every sentence adds essential information.

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?

Despite no output schema, description lists all returned fields (name, registration_number, address, registration_date). Annotations cover safety. All necessary context is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% but description adds value: 'case-insensitive' for name, 'omit to return first page', explains the implication of status='terminated' (larger dump size). Provides concrete examples in schema as well.

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 opens with 'Search FARA registrants' and clearly explains what FARA registrants are. It implicitly differentiates from siblings by mentioning how registration_number connects to other tools like list_foreign_principals and get_registrant_documents.

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?

Provides clear context: FARA has no server-side search, so client-side filtering is used; explains status='terminated' for larger dump. Lacks explicit when-not-to-use or direct alternative comparisons, but references sibling tools indirectly.

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

All Fara 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

A3.9/5.0
Disambiguation3/5

There are several clusters of tools with overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all do data-fetching/research with somewhat subtle differences. Polymarket tools also overlap (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, bet_research, polymarket_kalshi_spread). However, most tools have detailed descriptions that clarify their distinct roles, and the core data-lookup tools are differentiated by grounding level and scope.

Naming Consistency4/5

Most tools follow a consistent verb_noun or noun_verb pattern (e.g., search_registrants, list_foreign_principals, get_registrant_documents, subscribe, unsubscribe, remember, recall, forget, resolve_entity, validate_claim). Deviations include brand-name tools like ask_pipeworx, pipeworx_feedback, pipeworx_trending, and polymarket_kalshi_spread that mix conventions but are still readable and predictable within their domain.

Tool Count2/5

34 tools is heavy for a single MCP server, especially with multiple overlapping research entry points (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, suggest_questions). The broad data-router nature of the server explains the size, but it is still a large surface that would be better consolidated.

Completeness4/5

The server covers its visible domains well: data lookup, grounded verification, entity profiling, comparison, change tracking, subscription lifecycle, memory, and FARA-specific queries. Minor gaps exist (e.g., no direct tool for updating saved memory beyond forgetting/re-remembering, no tool to create custom alert types beyond the three supported categories), but the core workflows are complete.

Resources