Skip to main content
Glama

HemmaBo Host Booking Engine

by com.hemmabo

get_verified_stay_offer

Read-onlyIdempotent

Fetch, verify, and render a live host-domain signed VRP stay offer for exact dates and guest count. Verifies Ed25519 JWS against domain JWKS. Call after hemmabo_search_properties returns a host domain, or after verify_vacation_rental_node confirms a domain from outside search, always before quoting final price or a booking link. Read-only: must not lock a quote, create a booking, collect guest details, or start checkout. Route booking only to the signed direct_booking_url; fall back to hemmabo_booking_negotiate/hemmabo_booking_checkout only when this call returns no signed offer, for a configured non-VRP deployment, after explicit user confirmation. The parameters work as a set: pass the same domain, checkIn, checkOut and guests the guest used at search; checkIn must be strictly before checkOut, and the resulting night count — not the dates themselves — drives the signed price and the host capacity check, so changing either date re-prices the offer. Always pass language as the guest's actual conversation language so the rendered widget matches the guest; it never affects the signed price or availability, only formatting.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domainYesHost-owned domain without protocol or path (e.g. 'villaakerlyckan.se', 'myvilla.it'). Invalid: 'https://...', paths, ports, or booking URLs.
guestsYesTotal guest count as positive integer (e.g. 2, 4). Used by the host node for capacity validation and guest-tier pricing on the signed offer.
checkInYesRequested arrival date in YYYY-MM-DD format (e.g. '2026-11-14'). Must be strictly before checkOut. Use the same dates the guest requested in search.
checkOutYesRequested departure date in YYYY-MM-DD format (e.g. '2026-11-17'). Must be strictly after checkIn. Guest does not stay the departure night.
languageNoThe guest's conversation language, as a BCP-47 tag (e.g. 'en', 'sv', 'de', 'sv-SE') — ALWAYS pass this, matching the language the guest is chatting in, so the rendered widget's labels, dates and currency formatting match the guest instead of falling back to the rendering client's own locale (which can silently disagree with the conversation). Never changes the signed price value or availability — only how it is displayed.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNo
freshNoTrue when the signed offer is still within its validity/freshness window.
domainYesEchoed host domain that issued the signed offer.
guestsNoEchoed requested guest count.
checkInNoEchoed requested arrival date.
checkOutNoEchoed requested departure date.
verifiedYesTrue only when the host-domain offer signature and payload checks pass.
signatureNoEd25519/JWS verification details, including key id and verification status.
widget_mediaNoImages and media hydrated from the verified host discovery document for the ChatGPT widget.
agent_citationNoCitation permission and safe-to-quote status derived from the signed offer.
agent_guardrailsNoRules the agent must follow when presenting or acting on this offer.
payload_matches_offerNoTrue when the signed payload matches the structured offer returned to the agent.
official_offer_summaryNoSmall signed-offer summary for agents to quote without inventing price, availability, discounts, savings, comparisons, or booking details.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already mark the tool read-only and idempotent, and the description reinforces this with concrete prohibitions: 'must not lock a quote, create a booking, collect guest details, or start checkout.' It also adds meaningful behavioral detail such as night count rather than dates driving the signed price, and language never affecting price or availability. No contradiction with annotations.

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 longer than average but densely informative and well front-loaded, with the core action stated first and usage guidance following. Minor redundancy exists in repeating the language guidance and the checkIn/checkOut ordering, but given the complexity and the need to disambiguate from many siblings, the length is justified.

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?

The description is complete for an agent to select and invoke the tool correctly: it specifies when to call it, how the parameters interrelate, what side effects are forbidden, and how it differs from fallback booking tools. An output schema exists, so omitting return-value details is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description goes well beyond the schema by explaining that the parameters 'work as a set,' requiring the same domain and dates used at search, and by clarifying that the night count—not the dates—determines pricing. It also adds crucial guidance for the optional language parameter: always pass the guest's conversation language, since it only affects formatting.

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 opens with a specific verb-resource pair: 'Fetch, verify, and render a live host-domain signed VRP stay offer for exact dates and guest count.' It further sharpens the purpose by naming the JWS verification mechanism, which clearly separates this tool from the search and booking siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is explicit: call it after hemmabo_search_properties or verify_vacation_rental_node, and always before quoting a final price or booking link. It also states the fallback path to hemmabo_booking_negotiate/hemmabo_booking_checkout, with conditions including 'only when this call returns no signed offer' and explicit user confirmation.

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

All HemmaBo Host Booking Engine 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

A4.8/5.0
Disambiguation4/5

Most tools are cleanly separated by lifecycle stage (search, availability, quote, lock, checkout, status, cancel, reschedule), but get_verified_stay_offer, hemmabo_booking_quote, and hemmabo_booking_negotiate all touch pricing and could be confused in a quick selection. The descriptions do a strong job of disambiguating them, so only one or two pairs are genuinely ambiguous.

Naming Consistency4/5

The vast majority follow a consistent hemmabo_<domain>_<action> pattern with snake_case throughout. Minor deviations exist: hemmabo_booking_status is a noun rather than a verb, and get_verified_stay_offer / verify_vacation_rental_node break the hemmabo_ prefix convention.

Tool Count5/5

13 tools is well within the ideal range for a booking engine. Each tool maps to a distinct step in the guest journey or host onboarding flow, and none feel redundant or purely decorative.

Completeness5/5

The tool surface covers the full guest lifecycle: discovery, availability, pricing, price locking, checkout, pending booking creation, status lookup, cancellation, and rescheduling. Host-side onboarding is also represented, and the VRP verification/offer tools complete the trust and signed-offer path without leaving obvious dead ends.

Resources