Skip to main content
Glama

Search employers

search_employers
Read-onlyIdempotent

Find employers with Form 5500 health and welfare filings. All filters are optional and combine with AND. Returns up to 100 matches, largest first, with carriers, brokers, premium, comp rate, funding and renewal month. Union and multiple-employer plans are excluded unless include_union is true, and PEOs unless include_peo is true.

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": "search_employers"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWords to match in employer name, DBA, city, ZIP or EIN
tpaNoThird-party administrator from Schedule C (exact or partial), e.g. UMR, Meritain. Mostly self-funded plans with a trust.
zipNoZIP code prefix, e.g. 432
cityNoCity (prefix match)
sortNoSort order (default participants)
limitNoDefault 25
stateNoTwo-letter state code, e.g. OH
brokerNoBroker firm name (exact or partial), e.g. Lockton
offsetNo
carrierNoCarrier name (exact or partial), e.g. Cigna
changedNoOnly employers with any of these recent changes vs their previous filing, comma-separated: broker, carrier (main medical carrier), funding (fully insured <-> self-funded), headcount (participants up or down 25%+ and 100+), ended (plan ended: final filing), new (first Form 5500 filing under this EIN)
fundingNoMedical funding, comma-separated: Fully insured, Self-funded (stop-loss), Self-funded, Mixed, Unknown, No medical reported. Partial words like 'self-funded' match both self-funded labels.
has_lineNoLine of coverage the employer offers, e.g. Medical, Dental, Vision, Life, LTD, STD, Stop-Loss
industryNoIndustry sector, e.g. Manufacturing, Health care
include_peoNoInclude PEOs (professional employer organizations such as ADP TotalSource or Insperity), which file one plan for many client companies
missing_lineNoLine the employer does NOT have on Schedule A
employer_typeNoEmployer type: Company, Nonprofit, School or university, Health system, Government, Church, Union or trust fund, Association or MEWA, PEO, Other (identified by an AI model from the name)
include_unionNoInclude union (Taft-Hartley) and multiple-employer plans
broker_changedNoOnly employers whose broker of record changed in one of the two latest plan years
renewal_monthsNoRenewal months, 1-12
max_participantsNo
min_participantsNo
current_plan_year_onlyNoOnly employers whose latest filing is plan year 2025 or later

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / employer_type
      Added value: +{
      +  "description": "Employer type: Company, Nonprofit, School or university, Health system, Government, Church, Union or trust fund, Association or MEWA, PEO, Other (identified by an AI model from the name)",
      +  "type": "string"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / changed / description
      Previous value: -"Only employers with any of these recent changes vs their previous filing, comma-separated: broker, carrier (main medical carrier), funding (fully insured <-> self-funded), headcount (participants up or down 25%+ and 100+), ended (plan ended: final filing)"New value: +"Only employers with any of these recent changes vs their previous filing, comma-separated: broker, carrier (main medical carrier), funding (fully insured <-> self-funded), headcount (participants up or down 25%+ and 100+), ended (plan ended: final filing), new (first Form 5500 filing under this EIN)"
    • addedInput schema / properties / include_peo
      Added value: +{
      +  "description": "Include PEOs (professional employer organizations such as ADP TotalSource or Insperity), which file one plan for many client companies",
      +  "type": "boolean"
      +}
  3. Changed1 schema field changed
    • changedInput schema / properties / changed / description
      Previous value: -"Only employers with any of these recent changes vs their previous filing, comma-separated: broker, carrier (main medical carrier), funding (fully insured <-> self-funded), headcount (participants up or down 25%+ and 100+)"New value: +"Only employers with any of these recent changes vs their previous filing, comma-separated: broker, carrier (main medical carrier), funding (fully insured <-> self-funded), headcount (participants up or down 25%+ and 100+), ended (plan ended: final filing)"
  4. Changed1 schema field changed
    • addedInput schema / properties / changed
      Added value: +{
      +  "description": "Only employers with any of these recent changes vs their previous filing, comma-separated: broker, carrier (main medical carrier), funding (fully insured <-> self-funded), headcount (participants up or down 25%+ and 100+)",
      +  "type": "string"
      +}
  5. Changed1 schema field changed
    • addedInput schema / properties / tpa
      Added value: +{
      +  "description": "Third-party administrator from Schedule C (exact or partial), e.g. UMR, Meritain. Mostly self-funded plans with a trust.",
      +  "type": "string"
      +}
  6. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already flag readOnly/idempotent, so the description focuses on useful extra behavior: default ordering (largest first), the 100-result ceiling, and the default exclusion of union and PEO plans unless flags are set. Those default-exclusion rules are non-obvious and materially change results; it doesn't mention pagination semantics beyond the cap or whether counts are returned.

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?

Three tight sentences: purpose first, matching/ordering second, default exclusions third. No filler, and the most decision-relevant constraint (exclusions) is placed last but still prominent.

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 23-parameter read-only search with a rich schema and no output schema, this covers what the schema can't: ordering, result cap, and default exclusions. Remaining gaps are pagination guidance and sibling routing, both minor for a broad search tool.

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 87%, so nearly every parameter is already self-documented, and the description adds only the AND-combination rule and the include_union/include_peo exclusion defaults. It doesn't clarify output-affecting nuances of sort, offset/limit paging, or how the multi-value changed/funding filters interact.

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 ('Find employers with Form 5500 health and welfare filings') and discloses the return payload (carriers, brokers, premium, comp rate, funding, renewal month) plus ordering and cap. It does not explicitly distinguish itself from the sibling lookup tools get_employer/get_broker/get_carrier, though the search framing is clear enough.

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 explains that all filters are optional and AND-combined, and gives concrete exclusion rules for union/multiple-employer plans and PEOs with the flags that override them. What's missing is any explicit pointer to alternatives (e.g. get_employer for a single known record) or when the result cap of 100 means paging with offset.

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.

Resources