Skip to main content
Glama

AirTreks MCP

by io.github.Airtreks
OverviewDiscussionsAdmin

Submit a Trip Request (Consultant Handoff)

trip_idea_create
Destructive

Submit the customer's trip to AirTreks — a human travel consultant takes over from there. Automatically runs plan_route to attach the full routing analysis and carrier recommendations to the trip request, so the consultant starts informed, not cold. Use this when the customer is ready to get a real quote. Requires the customer's name, email, at least 2 cities (3-letter IATA codes), a departure date for every leg, and answers to AirTreks' planning questions — call once without questionsAnswers to receive the current questions to ask.

Input Schema

NameRequiredDescriptionDefault
nameYesCustomer full name (required — the consultant contacts them by name)
cabinNoCabin class preference
datesYesDeparture dates, one per leg (ISO format, e.g. '2026-09-15') — a trip with N cities needs N-1 dates, all required. If the customer is unsure, use their best estimates and set flexibleDates.
emailYesCustomer email address (required)
notesNoAdditional notes or special requests from the customer
phoneNoCustomer phone number
budgetNoBudget tier
citiesYesOrdered list of 3-letter IATA city/airport codes (e.g. ['SFO', 'NRT', 'BKK'])
sourceNoThe AI platform or app this conversation is running in, lowercase (e.g. 'chatgpt', 'claude', 'perplexity'). Only tells AirTreks which channel the request came through — never put customer details here. Omit it if you don't know.
passengersNoNumber of passengers (default 1)
preferencesNoTravel preferences: 'no-lcc', 'lounge-access', 'short-layovers', 'surface-ok'
agentContextNoSummary of what the AI agent learned about this trip (auto-generated routing analysis, customer preferences discussed, etc.)
sourceDetailNoFiner detail on source, such as the app or integration name (e.g. 'trip-pricer'). Never put customer details here.
flexibleDatesNoAre travel dates flexible?
questionsAnswersNoThe customer's answers to AirTreks' planning questions, keyed by question name (e.g. {"guidance": "I want expert guidance from humans"}). A JSON-encoded string of the same object is also accepted. Required, but don't guess the questions: call once without this — the response lists the current questions and their options to ask the customer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / source
      Added value: +{
+  "description": "The AI platform or app this conversation is running in, lowercase (e.g. 'chatgpt', 'claude', 'perplexity'). Only tells AirTreks which channel the request came through — never put customer details here. Omit it if you don't know.",
+  "type": "string"
+}
    • addedInput schema / properties / sourceDetail
      Added value: +{
+  "description": "Finer detail on source, such as the app or integration name (e.g. 'trip-pricer'). Never put customer details here.",
+  "type": "string"
+}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare destructive=true, openWorld=true and idempotent=false, so the risk profile is already flagged; the description usefully adds that a human consultant takes over externally and that plan_route runs automatically to attach routing analysis. It does not warn about duplicate/irreversible submissions or whether the request can be withdrawn, which would matter for a non-idempotent external write.

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?

Four sentences, front-loaded with purpose then behavior, usage trigger, and requirements — no filler or marketing padding. The final requirements sentence is dense but each clause carries a constraint the agent needs.

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 15-parameter tool with no output schema, the description covers required fields, the discovery call pattern, and the external consequence of submission. It stops short of describing the success response or error behavior, which is the main remaining gap.

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 baseline is 3, but the description adds real constraints beyond the schema: 'at least 2 cities', '3-letter IATA codes', 'a departure date for every leg', and the meta-instruction to call without questionsAnswers first. Those additions clarify how to populate required arrays that the schema alone leaves ambiguous.

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 ('Submit the customer's trip to AirTreks') plus the defining consequence (a human consultant takes over). This is clearly distinguishable from the sibling tools (fare_quote, plan_route, route_validate), and it even names plan_route to explain that it is invoked internally rather than by the agent.

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?

'Use this when the customer is ready to get a real quote' gives a concrete triggering condition, and the two-call questionsAnswers flow is spelled out precisely. It does not, however, state when NOT to use it (e.g. for pure pricing, use fare_quote/itinerary_quote), so the agent must infer the boundary against the other quote tools.

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

All AirTreks MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources