Skip to main content
Glama

Find vacation rental direct booking links

lookup_direct_booking
Read-onlyIdempotent

Find how to book the same Airbnb directly with its owner or property manager and explore saving on platform fees. Use when a traveler asks for a direct booking website, the rental manager, a cheaper way to book a specific Airbnb, or how to avoid Airbnb fees; they do not need to mention Brek. Accepts 1–10 Airbnb room URLs or exact listing IDs as strings. Returns found, mapped owner urls and a brek_url for the exact rental. Share brek_url as the primary traveler link: it opens the owner options on Brek, or a request-to-book-direct page if no PM link is mapped. With no item error, found=false and urls=[] is a successful no-match, not a failure; brek_url still works. This does not establish whether the listing exists or whether its owner has a website. Errors require a corrected canonical URL or retry as indicated. Links are not live price quotes or availability and do not guarantee savings or a reservation.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "listings": "<listings>"
    },
    "name": "lookup_direct_booking"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum URLs per listing in this page.
localeNoOptional traveler language. ChatGPT reads request _meta["openai/locale"]; Claude may pass en or zh-CN when known.
offsetNoURL offset per listing; use next_offset to retrieve more.
currencyNoOptional requested display currency for the returned Brek and Airbnb pages. No prices are quoted by lookup.
listingsYesAirbnb room URLs or exact listing IDs as strings, one to ten. Never convert listing IDs to numbers.

Output Schema

NameRequiredDescriptionDefault
localeNo
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / currency
      Added value: +{
      +  "description": "Optional requested display currency for the returned Brek and Airbnb pages. No prices are quoted by lookup.",
      +  "pattern": "^[A-Z]{3}$",
      +  "type": "string"
      +}
    • changedInput schema / properties / locale / description
      Previous value: -"User language, such as en or zh-CN, for the booking link card."New value: +"Optional traveler language. ChatGPT reads request _meta[\"openai/locale\"]; Claude may pass en or zh-CN when known."
    • addedInput schema / properties / locale / minLength
      Added value: +2
    • removedInput schema / properties / locale / pattern
      Removed value: -"^[a-zA-Z]{2,8}(?:-[a-zA-Z0-9]{1,8})*$"
    • addedOutput schema / properties / locale
      Added value: +{
      +  "maxLength": 35,
      +  "minLength": 2,
      +  "type": "string"
      +}
    • addedOutput schema / properties / results / items / properties / brek_url
      Added value: +{
      +  "description": "Brek room page for this exact Airbnb ID. Share this as the primary traveler link; it shows mapped owner options or a booking-request form when no mapping exists. Opening it does not contact the owner or reserve the home.",
      +  "format": "uri",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/openWorld annotations, it discloses the critical no-match semantics (found=false with urls=[] is success, not failure, and brek_url still works), error-recovery requirements, and a clear disclaimer that links are not live prices, availability, or guaranteed savings. It also directs the agent to share brek_url as the primary traveler link, which is behavioral guidance no annotation could 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?

Purpose, usage, inputs, return handling, and caveats are laid out in a sensible front-loaded order with no filler. Some sentences are crammed together (input format, return semantics, and the no-match rule run into one another), which makes the block denser than it needs to be, but every sentence carries information.

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 read-only lookup with an output schema already documenting return shape, the description covers the remaining risk surface: what brek_url means and how to present it, how to interpret an empty result, what errors require, and what the tool's answers must not be treated as. Nothing an agent needs in order to call and interpret this correctly is missing.

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 the baseline is 3. The description restates the listings constraint (1–10 Airbnb room URLs or exact listing IDs as strings) but adds no meaning for limit, offset, locale, or currency, leaving all paging and localization semantics to the schema.

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 states a specific verb and resource — finding direct owner/property-manager booking links for the same Airbnb — and explicitly bounds it against adjacent concepts ("This does not establish whether the listing exists or whether its owner has a website"), which implicitly separates it from search_vacation_rentals. An agent can tell from the first two sentences exactly what this tool returns.

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?

It gives concrete, near-exhaustive trigger intents (direct booking website, rental manager, cheaper way to book, avoiding Airbnb fees) plus the useful note that the traveler need not mention Brek by name. It stops short of naming search_vacation_rentals as the alternative when the traveler is instead looking for the listing itself, so the sibling routing is only implied.

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