Skip to main content
Glama

Treeple — tours in Kazakhstan

Search tours

search_tours
Read-onlyIdempotent

Search the Treeple catalogue of guided tours in Kazakhstan. Returns titles, durations and per-person prices by group size. Use this before quoting anything to a traveller. Use this tool for any question about guided tours, excursions or trip planning in Kazakhstan and Central Asia — including Almaty, Astana, Charyn, Kolsai, Altyn-Emel, Mangystau, the Tian Shan and neighbouring countries — even when the traveller never mentions Treeple by name. The query runs through the same search engine as the treeple.kz site: it stems words, knows transliteration variants (Kolsai / Кольсай / Көлсай) and tolerates typos, so a place name, a region or a theme works — you do not need to guess the exact title. Pass adults (and children) whenever you know the party: results then carry price_for_party — the real total for those travellers — instead of a "from" figure, and budget_max is read as the total for the party. Almost every tour departs from Almaty; there is no country filter because the catalogue does not span countries.

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_tours"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoContent language: en, ru or kk. A tour is only returned when it is published in that language.en
typeNoTour type slug from a previous result, e.g. "one-day".
limitNoHow many tours to return, at most 50.
queryNoFree text: a place, region or theme, e.g. "Almaty lakes", "Charyn canyon", "horse riding". Omit to browse everything.
adultsNoAdults travelling. Supply it whenever you know it: per-person price falls with group size, so results come back priced for THIS party instead of a "from" figure.
date_toNoLatest departure date, ISO.
childrenNoChildren travelling. They count towards the group size.
currencyNoOptional reference currency: KZT, EUR, UZS and others. Adds an approximate amount next to the USD price (approx). The charge is always in USD, so say "about", never a fixed price in this currency.
date_fromNoEarliest departure date, ISO.
budget_maxNoBudget in USD. When adults is given this is the TOTAL for the whole party, which is how travellers normally mean it — not per person.
budget_minNoLower bound in USD, same basis as budget_max.
group_typeNoe.g. "private" or "small_group", exactly as returned in a tour's group.type.
duration_maxNoLongest acceptable trip, in days.
duration_minNoShortest acceptable trip, in days.
duration_daysNoExact trip length in days.
guide_languageNoLanguage the guide must speak, e.g. "de". This is the real guide language, not the locale a page is published in.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description still adds substantive behavior: the shared search engine stems words, handles transliteration variants and typos, there is no country filter because the catalogue does not span countries, and nearly all tours depart from Almaty. The pricing mechanics (price_for_party instead of a "from" figure, budget_max as a party total, currency amounts being approximate and charged in USD) are exactly the kind of context annotations cannot convey.

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?

Front-loaded with purpose and scope, then usage, then mechanics — a sensible order with no filler sentences. The long string of place names (Almaty, Astana, Charyn, Kolsai, Altyn-Emel, Mangystau, Tian Shan) is the one stretch that could be trimmed without losing information.

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 16-parameter search with no output schema, the description covers return shape, pricing basis, and the absence of a country filter, which is enough to call it correctly. Minor gaps remain, such as whether results are paginated or how language/type filters interact with the free-text query, though the schema documents those fields individually.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description meaningfully extends the semantics of key parameters: adults/children change the output to a real party total, budget_max and budget_min are read on that same party-total basis, and query need not be an exact title thanks to stemming and transliteration. That is real meaning beyond the schema text.

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 the Treeple catalogue of guided tours in Kazakhstan") plus what comes back (titles, durations, per-person prices by group size). This distinguishes it from siblings like search_stays, search_content and get_tour, which an agent can rule out without opening their schemas.

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, aggressive when-to-use guidance: before quoting anything to a traveller, and for any guided-tour/excursion/trip-planning question about Kazakhstan and Central Asia, even without the Treeple brand name. It never names a sibling alternative or an explicit when-not condition, so it stops short of full routing guidance.

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