FedWatch — Federal Funding & Lien Watcher

licenses_search

Search normalized public license records from promoted official sources. Arizona ADHS remains a partial provider-name search; California DCC remains a one-page partial search with unverified total/paging; New York OCM (jskf-tt3q) is an official statewide Socrata dataset whose exact filtered count, schema evidence, source refresh time and resumable paging are returned on every call — OCM rows are explicitly classified as active/expired/surrendered/cancelled/revoked-if-observed/pending/proximity-protection/under-review rather than treating every row as an active license; Oregon OLCC (or_olcc_cannabis_licenses) and Connecticut establishments (ct_cannabis_establishments) are official Socrata registers with exact counts. fedwatch_sources carries a licenses entry for all 50 states + DC with each program's status. Unnecessary personal contact fields are not fetched.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "licenses_search"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum returned rows. Tier-capped for search; NY OCM supports explicit resume metadata when the exact filtered set is larger.
`county`	No	NY OCM only: exact county, e.g. 'Kings'
`status`	No	CA/NY: exact upstream status or status code, e.g. 'Active' or 'LICACT'; OR/CT: exact license status
`keyword`	No	Facility/business/license/application fragment; at least 2 characters for ADHS, optional for the Socrata/API sources
`page_size`	No	NY OCM only: bounded page size, 1-1000 (default 500)
`source_id`	No	Source id: azdhs_marijuana_facilities (default), ca_dcc_cannabis_licenses, ny_ocm_cannabis_licenses, or_olcc_cannabis_licenses, ct_cannabis_establishments
`license_type`	No	License type/code fragment, e.g. 'Retailer' or 'OCMRETL'
`record_class`	No	NY OCM only: active_license \| expired_license \| surrendered_license \| cancelled_license \| revoked_license \| pending_application \| proximity_protection \| license_under_review \| inactive_license
`start_offset`	No	NY OCM only: row offset for an explicit resume. Any non-zero start is deliberately partial.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 24, 2026

TDQS

A3.6/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses per-source truncation and paging limits, flags Arizona name-search partiality and California one-page partiality, promises exact counts and resumable paging for New York, and states that personal contact fields are excluded. It omits auth, rate limits, and the tier-cap threshold values.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, but the body is a single sprawling semicolon chain mixing source caveats, classification vocabulary, and privacy notes. Every clause is relevant, yet a bulleted per-source breakdown would make the same information far more scannable.

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?

For a 9-parameter, annotation-free search tool with no output schema, the description covers source scope, partiality, paging/resume behavior, and row classification semantics. It still leaves response shape and default limit behavior unstated, but an agent has enough to call it correctly.

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%, so the schema already documents all nine parameters well. The description adds only scattered context (tier-capped limits, NY resume metadata, ADHS keyword minimum) that largely restates the schema's own parameter descriptions, so it earns the baseline rather than more.

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 first sentence gives a specific verb and resource: search normalized public license records from promoted official sources. That is enough to tell it apart from permits_search or businesses_search, though the description never explicitly names a sibling it should be preferred over or deferred to.

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

Usage Guidelines3/5

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

The description explains the coverage status of each source and points to fedwatch_sources for the 50-state overview, which implicitly guides source selection. It does not state when to use this tool versus permits_search, businesses_search, or the other record-lookup siblings, and offers no explicit exclusions.

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

All FedWatch — Federal Funding & Lien Watcher 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.

Resources

Need Help?