Skip to main content
Glama

Swift Agent Network: Local Agents, Movers & Contractors

Search network members

search_members
Read-onlyIdempotent

Find members of the Swift Agent Network: licensed or registered local businesses in the US (real estate agents, insurance agents, moving companies, bus and limo operators, contractors). Each member was matched to a state license file or the FMCSA register. Filter by state, city, line of work and name. The network lists members; it does not rate or rank them. If no member is in the city asked for, the state's members are returned with city_fallback true. Each member and the answer itself carry the URL of the city page (city_page, https://swiftagentnetwork.com///) and the state page (state_page, https://swiftagentnetwork.com//) that list every member there: link those for a whole town. A member may carry local_answers: questions about where they work that they answered in their own words, each read by a person before it was published (for a city search, the ones about that city first). A member who takes bookings and has an open time in the next 7 days carries book: their next open time (next_open, with their UTC offset), time zone, meeting length and book_url, the page where the person picks a time and books it themselves.

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_members"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity name, e.g. "Austin".
lineNoLine of work: real-estate, insurance, movers, bus, contractors or other. Common words such as "realtor", "moving company" or "plumber" work too.
nameNoPart of the member's name.
limitNoMost results to return.
stateNoTwo-letter US state code or state name, e.g. "TX" or "Texas".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond them: the city_fallback=true behavior when no local member exists, the presence of human-reviewed local_answers, and the book/next_open payload (with UTC offset, time zone, meeting length, book_url) for members accepting bookings. It also discloses the city_page/state_page URLs returned, which the absence of an output schema makes essential.

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?

Purpose and population are front-loaded, and every sentence carries information an agent needs — fallback rule, URLs, local_answers ordering ("for a city search, the ones about that city first"), and booking fields. It is a single dense block with no paragraph breaks, so the return-value detail at the end is harder to scan than it could be, but there is little redundancy to cut.

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, a search tool of this complexity needs the description to explain return shape, and it does: city_fallback, city_page/state_page link templates, local_answers with ordering and moderation notes, and the nested book object with next_open, UTC offset, meeting length and book_url. Nothing material for correct invocation or result interpretation is missing.

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 coverage is 100%, so the schema already documents each parameter; the description still adds meaning by framing the four filters as a combined query and by explaining the behavioral consequence of the city parameter (state-level fallback flagged with city_fallback). It does not elaborate on name matching or limit semantics beyond the schema, so it is short of a 5.

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?

Opens with a specific verb+resource ("Find members of the Swift Agent Network") and defines exactly who the members are (licensed/registered local businesses matched to a state license file or FMCSA register), plus the filterable facets. This is clearly distinguishable from get_member and open_times by scope, though it never names those siblings to route the agent explicitly.

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?

Gives useful context — "The network lists members; it does not rate or rank them" and the fallback rule when a city has no members — which tells the agent what to expect from a city/state search. However, it never says when to use this versus get_member or open_times (e.g., for one member's details or for availability), leaving the agent to infer routing from the filter list.

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.