Skip to main content
Glama

VoiceAssistants

Find local businesses

find_businesses
Read-onlyIdempotent

Search the VoiceAssistants directory of local US businesses by what the person needs (a trade such as "plumber", a service such as "drain cleaning", or a business name) and where (city and two-letter state). Optional filters: open right now, available today, or a maximum starting price in US dollars. Returns up to limit businesses, each with an id to pass to get_business, get_hours or answer_question. If nothing matches exactly, the search is widened and relaxed says how. Results are ordered by how recently each business was verified, never by payment. Read spoken aloud as the answer.

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": "find_businesses"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity name, for example "Stuart".
limitNoHow many to return. Default 5.
queryNoWhat is needed: a trade ("plumber"), a service ("AC repair") or a business name. Plain words.
stateNoTwo-letter US state code, for example "FL".
open_nowNoOnly businesses open at this moment in their own time zone.
available_todayNoOnly businesses that have confirmed today that they can take new work today.
max_starting_priceNoOnly businesses with a published starting price at or below this many US dollars.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so safety is covered; the description still adds substantial behavior the agent cannot infer: results are capped at `limit`, an inexact search is silently widened with a `relaxed` signal, ordering is by verification recency and "never by payment", and `spoken` must be read aloud. The anti-commercial-bias ordering note and the relaxation fallback are exactly the kind of non-obvious traits that change how an agent interprets and presents results.

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?

Five sentences, each doing distinct work: purpose and location, optional filters, return cap and id hand-off, relaxation behavior, ordering policy, and the spoken-field instruction. It is front-loaded with purpose and contains no repeated or filler phrasing.

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 no output schema, the description takes on the return-shape burden and does so: result cap, the `id` field, the `relaxed` indicator and the `spoken` field are all named. For a read-only search with fully documented parameters, an agent has everything needed to call it and to interpret the response.

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 explains city, state, limit, query and the three filters in comparable detail. The description restates the filter group ("open right now, available today, or a maximum starting price in US dollars") and adds no syntax, default or interaction semantics, such as whether the filters combine with AND. Baseline 3 applies when the schema carries the load.

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 opens with a specific verb and resource ("Search the VoiceAssistants directory of local US businesses") and immediately breaks the query into its two axes, what is needed and where. It also lists the concrete trade/service/name forms the query accepts, which separates this discovery tool from the detail-oriented siblings get_business, get_hours and answer_question.

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 tells the agent the situation this tool serves (find a business by need plus location) and explicitly routes follow-up work by saying each result carries an `id` to pass to get_business, get_hours or answer_question, so the search-versus-detail boundary is clear. It stops short of stating when not to call it, e.g. what to do when the caller already has an id.

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