Skip to main content
Glama
Sign In
Hotelbeds MCP Server

Hotelbeds MCP Server

by karanrao
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Create booking

create_booking

Book a hotel rate using two-step surface-and-reconfirm: first call gets live price, second commits with acceptedNet. Re-confirms if price moves beyond tolerance.

Instructions

Book a rate. Two-step surface-and-reconfirm: call once WITHOUT acceptedNet to surface the live price, then again WITH acceptedNet set to that price to commit. Re-surfaces if the price moves beyond tolerance.

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": {
      "rateKey": "<rateKey>",
      "holderName": "<holderName>",
      "holderSurname": "<holderSurname>",
      "paxes": "<paxes>"
    },
    "name": "create_booking"
  }
}

Input Schema

NameRequiredDescriptionDefault
paxesYesAll guests; must match the rate's occupancy.
remarkNo
rateKeyYesrateKey to book (from search_hotels or check_rate).
toleranceNoAllowed % price increase before re-confirmation is required.
holderNameYesLead guest first name.
acceptedNetNoThe net price you have agreed to pay. OMIT on the first call to receive a price quote. On the second call, set it to the currentNet the first call returned, to commit.
holderSurnameYesLead guest surname.
clientReferenceNoYour own booking reference for reconciliation. Auto-generated if omitted (Hotelbeds requires one).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden; it discloses the non-obvious two-phase quoting/committing behavior and the price-tolerance re-confirmation loop, which the schema alone would not make clear. It omits irreversibility/permissions/payment consequences and the fact that a successful second call creates a real reservation, which are material for a mutation tool.

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?

Three short sentences, zero filler, and the critical first-vs-second-call distinction is front-loaded before the tolerance caveat. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description should carry return-value expectations; it conveys that the first call yields a live price and the second commits, but not what a committed booking returns (reference, status) or failure modes. Adequate for the happy path, incomplete for the full call cycle.

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 88%, so the schema already documents acceptedNet's quote-then-commit semantics and tolerance. The description reinforces the acceptedNet usage but adds no syntax, format, or edge-case detail beyond it, so the baseline 3 applies.

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+resource ('Book a rate') and immediately scopes it with the two-step surface-and-reconfirm protocol. An agent can distinguish this committing action from the sibling read tools (search_hotels, check_rate) without opening the schema.

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?

Gives explicit sequencing: call once WITHOUT acceptedNet to get a price, then again WITH acceptedNet set to that price to commit, and notes re-surfacing when price moves beyond tolerance. It does not name sibling alternatives (e.g. check_rate) or when-not-to-use, so it stops short of a 5.

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

Deploy Server

Other Tools