Skip to main content
Glama

Warn Search

warn_search
Read-onlyIdempotent

Search US WARN Act layoff and plant-closure notices filed with state labor departments, the legally required 60-day advance notice of a mass layoff or site closure. Returns employer name, site city and county, notice date, layoff effective date, number of workers affected, and whether the filing is a layoff or a closure. Answers "which employers filed layoff notices in Texas this year", "layoff filings above 200 workers since June", "WARN notices in Suffolk County". Covers the states named in states_covered on every response.

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": {
      "since": "2026-01-01",
      "state": "TX",
      "min_employees": 200
    },
    "name": "warn_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax notices to return (default 50, max 500).
sinceNoEarliest WARN notice date, YYYY-MM-DD.
stateNoTwo-letter state code, e.g. "TX". Omit to search every covered state.
companyNoEmployer name, free text. Matched loosely against the filed legal name, so "Tesla" finds "Tesla, Inc.".
min_employeesNoOnly notices affecting at least this many workers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so safety and idempotency need no restatement. The description adds one genuinely useful behavioral note that coverage is limited to states listed in states_covered, though it neither names those states nor warns that absence of a notice in an uncovered state means nothing.

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?

It is front-loaded with the core definition followed by return fields, then illustrative queries, so an agent can stop reading early and still act. The example queries are the longest element but do real work in disambiguating filtering behavior, though the description runs longer than strictly necessary given the fully documented schema.

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?

With no output schema, the description correctly takes on the burden of listing return fields (employer, city, county, notice date, effective date, worker count, layoff vs. closure). For a five-parameter, all-optional read tool this is close to complete; the only material gap is that the covered states are referenced but never enumerated.

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 description coverage is 100%, so the baseline is 3, and the description pushes slightly past it by restating the practical filters in natural language: worker-count thresholds ("above 200 workers") and date bounds ("since June"). Remaining parameters such as company matching and limit are left entirely to the schema, which is acceptable since the schema documents them 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 names a specific source and resource: US WARN Act layoff and plant-closure notices filed with state labor departments, and it explains the domain meaning (60-day advance notice of mass layoff/closure). It further enumerates the returned fields and gives three concrete question shapes, so an agent knows exactly what this retrieves.

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 example queries (state+year, worker threshold+date, county) imply the contexts where this tool applies, which is useful routing signal. However, it never states when to use this versus warn_company, warn_recent, or warn_coverage, and it offers no exclusions, so selection guidance is inferred rather than explicit.

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.