Skip to main content
Glama

Gondola Award Travel Search

by ai.gondola

search_flights

Read-only

Search for flights by route and date. Returns cash-priced options ranked for the traveler — weighing their airline loyalty/status and travel history alongside flight quality, not price alone — 10 options per page. Call again with page=2, 3, ... to see more options if none of the first page fit.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoLeave as "browse" (default). "book" is a restricted alpha — only use it if the user explicitly asks to book a flight.browse
pageNo1-based results page, 10 options per page. Increment to see more options.
originYesOrigin airport code or city (e.g. "LAX", "SFO", "New York").
airlinesNoOptional airline codes or names, e.g. ["UA"] or ["United"]. Used only in "browse" mode and passed to the Google Flights search API.
max_stopsNoOptional maximum stops per direction in "browse" mode. Use 0 for nonstop only.
cabin_classNoOptional cabin class: "economy", "premium economy", "business", "first".
destinationYesDestination airport code or city (e.g. "NRT", "LHR", "Paris").
return_dateNoOptional return date in YYYY-MM-DD format for a round trip. Read the labels on the results: a price marked 'round trip' already covers both directions, while results split into separate outbound and return sections are one-way prices whose sum overstates the real round-trip fare.
departure_dateYesDeparture date in YYYY-MM-DD format.
num_passengersNoNumber of passengers.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

TDQS

A4.5/5.0
Behavior5/5

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

The description adds meaningful behavioral detail beyond the readOnlyHint annotation: results are cash-priced, ranked by airline loyalty/status and travel history alongside flight quality rather than price alone, and limited to 10 options per page. This is valuable context an agent needs to interpret results correctly.

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 two well-structured sentences. The first sentence immediately states the core purpose, and the second adds essential behavioral context and a practical pagination instruction without unnecessary fluff.

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 search tool with a rich input schema, output schema, and clear annotations, the description covers the key non-obvious behavior: personalized ranking, cash-priced options, and pagination. Nothing critical is missing for an agent to invoke the tool correctly.

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 every parameter is already documented in the input schema. The description's mention of route and date adds no new parameter-level information beyond what the schema provides, so the baseline score of 3 is appropriate.

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?

The description clearly states the tool's action and resource: 'Search for flights by route and date.' It also specifies that it returns cash-priced options ranked by traveler-specific factors, distinguishing it from similarly named sibling search tools like search_hotels and search_vehicles.

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?

The description gives clear context for when to call the tool: when the user wants to search flights by route and date. It also guides pagination ('Call again with page=2, 3, ...'). It does not explicitly name alternative tools or state when not to use it, but the usage context is clear enough.

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

All Gondola Award Travel Search 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

A4.2/5.0
Disambiguation5/5

Each tool targets a distinct resource and action; no two tools have overlapping purposes. For example, search_hotels, get_hotel_details, get_hotel_reviews, and get_hotel_stats all address different aspects of hotel research.

Naming Consistency5/5

Tool names follow consistent patterns: search_ for searches, get_ for retrievals, book_ for bookings, and a few standalone verbs like cancel_, create_, delete_. All use snake_case with no mixing of conventions.

Tool Count4/5

With 31 tools, the server is on the high side but covers a broad domain (hotels, flights, vehicles, loyalty, payments). Most tools are justified, though a few hotel analysis tools could potentially be consolidated.

Completeness3/5

Hotels and vehicles have near-complete lifecycle coverage (search, details, book, manage), but flights are missing a book_flight tool, and hotel cancellation is not present. These gaps limit completeness.

Resources