Skip to main content
Glama

Tuki — Travel Marketplace (Chile y Latinoamérica)

by cl.tuki

Recomendación natural-language

recommend
Read-onlyIdempotent

Natural-language recommendation. Pass the user query verbatim (e.g. "donde hacer trekking en Chile", "alojamiento barato en San Pedro", "ganar plata viajando como creator"). Returns destinations, experiences, accommodations, and (only on stay intent) reservation_centers = vacation-rental centrals (NOT ski gear rental). Supports optional price_min/price_max in CLP. Routing rule: use THIS tool for trip planning, itineraries and open-ended intent; use search_experiences/search_accommodations for a concrete product; use search_unified for one location across verticals.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesUser question in natural language.
price_maxNoOptional maximum experience price in CLP (FX-normalized).
price_minNoOptional minimum experience price in CLP (FX-normalized).

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. Description adds valuable context: pass query verbatim, returns specific entity types, reservation_centers only on stay intent with clarification it is NOT ski gear rental, and price filters in CLP. No contradiction with annotations.

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?

The description is appropriately sized (~90 words) and each sentence earns its place: purpose, examples, return types, special case clarification, price support, and routing. Front-loaded with a clear statement and no redundancy.

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?

For a complex recommendation tool with no output schema, the description covers return types, intent-dependent behavior, price filters, and routing to siblings. Provides enough context for an agent to select and invoke the tool correctly without requiring additional details.

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?

Input schema has 100% coverage with descriptions for query, price_min, price_max. Description adds 'Pass the user query verbatim' and examples for query, which supplements the schema's generic 'User question in natural language.' Price semantics are already fully documented in the schema, so the description's mention adds marginal value beyond baseline.

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?

Description clearly states 'Natural-language recommendation' with specific examples of user queries and explicitly distinguishes from sibling tools via routing rule. The verb 'recommend' and return types (destinations, experiences, accommodations) make the resource and scope unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Contains an explicit 'Routing rule' stating when to use THIS tool (trip planning, itineraries, open-ended intent) versus search_experiences/search_accommodations for concrete products and search_unified for one location. Provides example queries to illustrate appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Tuki — Travel Marketplace (Chile y Latinoamérica) toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Every tool targets a distinct resource or action: get_* tools retrieve details for specific entity types, search_* tools query specific verticals, and list_* tools enumerate categories. The potential overlap between search_accommodations and search_hotels is explicitly disambiguated in descriptions, and search_unified vs per-vertical searches have clear routing rules.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern: get_*_detail for lookups, search_* for queries, list_* for enumerations, and recommend as the sole one-word but still predictable exception. Naming is uniform with snake_case throughout, making the overall structure highly predictable.

Tool Count4/5

With 23 tools, the server is on the heavier side, but the breadth of verticals (accommodations, cars, events, experiences, hotels, destinations, bus routes, travel guides, solutions) justifies each tool's presence. The number is slightly above the ideal but still well-scoped for a multi-category marketplace.

Completeness5/5

The tool surface covers the full browsing and recommendation lifecycle: search and list across verticals, retrieve detailed information for any entity, access editorial travel guides, and generate checkout URLs for booking. No critical operations are missing for the server's purpose as a read-only recommendation and conversion layer.

Resources