Skip to main content
Glama

Search local businesses

search_businesses
Read-onlyIdempotent

Find local businesses in Connecticut and Massachusetts by trade, problem, name and place, nearest first. Understands problems as the trade that fixes them ('no heat' = HVAC, 'overflowing toilet' = plumbers, 'car won't start' = towing). Returns 20 results a page with phone, address, website, open-now status when the hours are known, whether a contractor's state license was verified, and the TownIndex page url.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_businesses"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage of 20 results.
queryYesWhat and where in plain words: a trade, a problem or a business name, and a town or ZIP code. Examples: 'plumber in Wolcott', 'no heat 06114', 'pizza Hartford', 'locksmith Worcester MA'.
stateNoOnly this state.
near_zipNoThe user's ZIP code: used to rank by distance when the query names no place.
open_nowNoOnly businesses open right now (by their hours, their emergency hours, or on call). If none is known to be open, all matches are returned instead, with fallback set.
emergency_nowNoOnly businesses taking emergency calls right now (24/7 emergency service or on call). If none is known, all matches are returned instead, with fallback set.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare this is a safe, idempotent, closed-world read, so the description is not needed to establish safety. It still adds real behavioral context beyond them: fixed page size of 20, nearest-first ordering, and the fallback rule where open_now/emergency_now return all matches when nothing is known open. Return-field disclosure (phone, address, open-now status, license verification, page URL) further reduces uncertainty about what comes back.

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?

Two sentences, purpose front-loaded, with no filler or hedging. The second sentence is a dense enumeration of return fields, but given there is no output schema that information earns its place rather than being padding.

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?

With six parameters and no output schema, the description must carry both the filter semantics and the result shape, and it does: geography, ranking, page size, and returned fields are all stated. Combined with annotations covering safety and the fully described schema, an agent has everything needed to call this 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 coverage is 100% and each of the six parameters carries its own description, including the query examples and the near_zip ranking rule, so the schema already does the heavy lifting and the baseline of 3 applies. The description contributes marginally by explaining that near_zip ranks by distance only when the query names no place, reinforcing the schema rather than extending it.

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 uses a specific verb and resource ('Find local businesses') and pins down scope precisely: two states, searchable by trade, problem, name and place, ranked nearest first. An agent immediately knows this is a multi-result search rather than a single-record fetch. It never names the sibling get_business or on_call_near, so differentiation from those alternatives is left to inference.

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?

There is useful guidance on how to phrase the query, including the problem-to-trade mapping ('no heat' = HVAC, 'overflowing toilet' = plumbers), which is genuine usage help. However, there is no explicit statement of when to use this tool instead of get_business or on_call_near, nor any exclusions or prerequisites. Usage is therefore implied rather than directed.

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