Skip to main content
Glama

Nlrb Search

nlrb_search
Read-onlyIdempotent

Search US National Labor Relations Board cases by employer, union, or case number, unfair labor practice charges (C cases: CA against an employer, CB against a union) and union representation/election petitions (R cases: RC, RD, RM). Returns case number, case name, date filed, open/closed status, city and NLRB region for each match, plus the total number of matching cases. Answers "is Starbucks facing an NLRB charge", "labor board complaints against Amazon", "union election petitions at Trader Joe's", "what NLRB cases involve Teamsters Local 705". Filter by case type, status, date filed, and NLRB region.

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": {
      "limit": 3,
      "query": "Starbucks Corporation"
    },
    "name": "nlrb_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoZero-based page of results, for paging past the first `limit` cases.
sortNo"newest" (default), "oldest", or "relevance".
limitNoMax cases to return (1-50, default 10).
queryYesEmployer name, union name, or a full case number such as "10-CB-393760". Matched full-text against case names; case-insensitive.
regionNoNLRB region number, e.g. "10" (Atlanta), "29" (Brooklyn). Two digits; single digits are zero-padded.
statusNoRestrict to "Open", "Closed", or "Open - Blocked".
case_typeNoRestrict to "C" (unfair labor practice charges) or "R" (representation/election petitions). Omit for both.
filed_sinceNoOnly cases filed on or after this date (YYYY-MM-DD).
filed_beforeNoOnly cases filed on or before this date (YYYY-MM-DD).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is covered. The description adds real value beyond that, and beyond the absent output schema, by naming the returned fields (case number, name, date filed, status, city, region) and the total match count. It does not discuss paging behavior or result caps, though those are documented in the schema.

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?

The core scope and case-type taxonomy are front-loaded, and the return-field sentence follows logically. The string of four natural-language user questions is slightly redundant and could be trimmed to two without losing retrieval value, but overall the prose earns most of its space.

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 nine-parameter search tool with no output schema, the description covers what is searched, what comes back, and which dimensions can be filtered. Remaining gaps are minor and largely absorbed by the fully documented schema: sort/paging semantics, and any statement about how broad full-text name matching behaves.

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 100%, including per-parameter notes on region zero-padding, date formats, and limit bounds, so the schema already carries the burden. The description contributes mainly the C-subcode (CA employer / CB union) and R-subcode (RC/RD/RM) breakdown, which is helpful domain framing but does not map onto additional accepted values. Baseline 3 applies when the schema does the heavy lifting.

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 ("Search US National Labor Relations Board cases") and immediately narrows scope to employer, union, or case number. It further disambiguates the two case families (C charges with CA/CB subcodes, R petitions with RC/RD/RM subcodes), which an agent cannot infer from the tool name alone.

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?

The four quoted example questions ("is Starbucks facing an NLRB charge", "union election petitions at Trader Joe's") give concrete when-to-use context, and the closing sentence enumerates the filterable dimensions. It stops short of explicitly excluding alternatives such as fetching a single case by number, so the boundary with nlrb_case is left implicit.

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.