Skip to main content
Glama

uPlanny — салоны и запись

Поиск салонов

search_salons
Read-onlyIdempotent

Search businesses (beauty salons, barbershops, nail and brow studios, massage, spa, clinics and other appointment-based places) in the uPlanny catalogue. Filter by text, category, place («рядом», «около», «недалеко», «возле метро» → near or lat/lng with radiusKm), city, salon rating and price; paginated. Each item has the salon slug (for get_salon), rating {average, reviews} or null when there are no reviews yet, priceFrom (cheapest service, RUB), distanceKm when a place was given, and bookingUrl.

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_salons"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude of the place to search around (instead of `near`).
lngNoLongitude of the place to search around (instead of `near`).
cityNoOnly businesses whose address contains this text, e.g. a city «Казань». Ignored when a place is given.
nearNoA place to search around: address, metro station or landmark, with the city — «Москва, метро Сокол», «Казань, Баумана 10». Used for «рядом», «около», «недалеко», «поблизости».
pageNoPage number, from 0.
sortNoOrder. Default: distance when a place is given, otherwise rating.
queryNoFree text: salon name, service, master's name. Russian works best, e.g. «маникюр», «стрижка мужская».
categoryNoCategory id from list_categories.
maxPriceNoHas a service costing at most this, RUB.
minPriceNoHas a service costing at least this, RUB.
pageSizeNoItems per page, 1–20 (default 10).
radiusKmNoSearch radius around the place, km (default 3, max 50; ~1 for «в шаговой доступности»).
maxRatingNoSalon rating at most this (1–5).
minRatingNoSalon rating at least this (1–5). Salons without reviews are excluded when any rating bound is set.
minReviewsNoWith a rating bound: at least this many reviews (default 1).

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 closed-world, so the safety profile needs no restating. The description adds real behavioral detail beyond them: pagination exists, results carry rating {average, reviews} or null when unreviewed, priceFrom is the cheapest service in RUB, and distanceKm appears only when a place was supplied.

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 dense sentences, front-loaded with what is searched, then filtering capability, then the shape of each result. The quoted Russian place phrases are functional rather than filler, though the filter clause is a long run-on that could be broken for scanability.

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?

With 15 optional parameters and no output schema, the description does the heavy lifting by summarizing exactly which fields come back and how to chain into get_salon via `slug`. Only minor gaps remain, such as total-count/pagination metadata, which an agent would likely want to know.

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 all 15 parameters are already documented, including the near-synonym mapping, radius default/max, pageSize bounds and the rating-bound rule excluding unreviewed salons. The description restates those filters at a higher level and adds essentially no syntax or default information the schema lacks, so the baseline 3 applies.

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 (search) and resource (businesses in the uPlanny catalogue) and enumerates the included verticals (beauty salons, barbershops, nail/brow studios, massage, spa, clinics). It also distinguishes itself from get_salon by naming the `slug` as the follow-up key, so an agent can route without opening another schema.

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?

Gives clear context for the main filtering modes — text, category (with an explicit pointer to list_categories), place phrasing like «рядом»/«около метро» mapped to `near` or lat/lng with radiusKm, city, rating and price — plus a note that city is ignored when a place is given. It stops short of explicitly contrasting with search_services or saying when not to use it, so it is clear but not fully exclusionary.

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