Skip to main content
Glama

Abstraxn Agent Layer

by io.github.sandeep-antier

Flight / hotel search (pay-per-call)

travel.search
Read-onlyIdempotent

Flight and hotel search, paid per call in USDC/USDm directly from the caller's own wallet via the x402 protocol — no Abstraxn account needed. Pick one action:

  • flight_search ($0.02): live flight fares via Google Flights. Requires origin, destination, departureDate. Optional returnDate, adults, children, travelClass, stops, maxPrice, currency.

  • hotel_search ($0.02): live hotel prices/ratings via Google Hotels. Requires q (city or hotel name), checkInDate, checkOutDate. Optional adults, children, sortBy, minPrice, maxPrice, hotelClass, currency.

Prices above are indicative — the exact charge for a given call is always whatever the live payment challenge specifies for that request. The first call (no paymentPayload) returns paymentRequired; retry with the same arguments plus paymentPayload to complete payment and get the real result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNohotel_search: city or hotel name to search for, e.g. "hotels in Paris".
stopsNoflight_search: stop preference — 0=nonstop only, 1=up to 1 stop, 2=up to 2 stops. Optional.
actionYesWhich travel operation to perform.
adultsNoflight_search / hotel_search: number of adult passengers/guests. Optional.
originNoflight_search: departure airport IATA code, e.g. "JFK".
sortByNohotel_search: sort order — 3=lowest price, 8=highest rating, 13=most reviewed. Optional.
childrenNoflight_search / hotel_search: number of children. Optional.
currencyNoflight_search / hotel_search: currency code, default "USD".
maxPriceNoflight_search / hotel_search: maximum price filter. Optional.
minPriceNohotel_search: minimum price per night filter. Optional.
hotelClassNohotel_search: star rating filter, 2-5. Optional.
returnDateNoflight_search: return date for round trips, YYYY-MM-DD. Optional.
checkInDateNohotel_search: check-in date, YYYY-MM-DD.
destinationNoflight_search: arrival airport IATA code, e.g. "LAX".
travelClassNoflight_search: cabin class — 1=Economy, 2=Premium Economy, 3=Business, 4=First. Optional.
checkOutDateNohotel_search: check-out date, YYYY-MM-DD.
departureDateNoflight_search: departure date, YYYY-MM-DD.
paymentPayloadNox402 payment payload from a previous `paymentRequired` challenge. Omit on the first call.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNo
paymentRequiredNo

TDQS

A4.6/5.0
Behavior5/5

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

The description goes well beyond the annotations, disclosing that calls are paid per use via x402 from the caller's own wallet, no account needed, pricing is indicative, and the two-step payment challenge flow. This explains the tool's key behavioral trait (pay-per-call) that annotations alone don't 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?

The description is lengthy but well-structured with bullet points and action-specific blocks. Every sentence provides necessary information (pricing, parameters, payment flow). It is appropriately detailed for a tool with 18 parameters and two modes, though slightly dense.

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 tool with two actions, 18 params, and a payment protocol, the description covers the purpose, usage, required params, payment flow, and pricing. An output schema exists, so return values are covered. The description gives the agent everything needed to invoke the tool correctly.

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 baseline is 3. The description adds value by grouping parameters under each action, marking which are required vs optional, and explaining the paymentPayload special role. This helps the agent understand the parameter relationships beyond individual schema entries.

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 explicitly states 'Flight and hotel search' with a clear verb and resource, and distinguishes the two actions (flight_search and hotel_search) with their specific purposes. It is clearly differentiated from sibling tools like network.* or market.crypto, which are unrelated to travel.

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 provides detailed usage context: how to choose an action, required and optional parameters per action, and the exact payment flow (first call returns paymentRequired, then retry with paymentPayload). It doesn't mention alternatives or exclusions, but sibling tools are unrelated so no explicit 'when not to use' is needed.

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

All Abstraxn Agent Layer 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

A4.1/5.0
Disambiguation4/5

Tools are broadly distinct by domain (market, network, social, travel, web3), but some overlap exists between market.crypto and network.token_price (both provide token prices), and between network.token_info and web3.lookup's token_metadata action. However, the descriptions clarify the differences well.

Naming Consistency3/5

Tool names use a domain.subdomain pattern (e.g., market.crypto, network.gas_info), but the subdomains mix styles: dots (market.crypto), underscores (network.token_info), and plain names (travel.search). Additionally, actions within tools like 'places.lookup' have inconsistent naming (text_search_full vs. solar_building_insights).

Tool Count4/5

With 11 tools covering diverse domains (crypto, network, places, social, travel, web3), the count is reasonable. However, some tools encapsulate many actions (e.g., market.crypto has 6 actions, places.lookup has 12), hinting at a slightly heavy surface, but overall it fits the broad scope.

Completeness4/5

The tool set covers core workflows for each domain: crypto market data, network operations (block, gas, transfers, tokens), place search, social profile lookup, travel search, and web3 lookups. Minor gaps exist (e.g., no tool for sending transactions or managing user accounts), but the stated purpose (agent layer for diverse tasks) is mostly fulfilled.

Resources