Skip to main content
Glama
Sign In

OKstays

by com.okstays
OverviewDiscussionsAdmin

Hotel details

get_hotel
Read-onlyIdempotent

Use this when the user asks about one hotel: why it scores as it does, or whether it's quiet, clean or good for sleep or work. Returns the Comfort Score breakdown, what the scores rest on, the five must-haves, its strengths and complaints with the reason behind each score, price, the city tax where we know it and its okstays.com link. Pass focus with what the user asked about; detail='full' adds every scored signal (about four times longer). Read-only, no sign-in.

Input Schema

NameRequiredDescriptionDefault
focusNoSignals the user asked about, as filter ids or names (e.g. ['quiet', 'bed', 'wifi']); always included with their reasons.
adultsNoGuests per room (1-8), if given.
detailNosummary (default) or full: every scored signal with its explanation, about four times longer.
checkinNoUser's check-in date, YYYY-MM-DD (e.g. 2027-03-12), if given: links then open on this stay.
checkoutNoCheck-out date, YYYY-MM-DD (e.g. 2027-03-15).
hotel_idYesHotel id (numeric string) from search_hotels.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / adults / description
      Previous value: -"Guests per room, if given."New value: +"Guests per room (1-8), if given."
    • changedInput schema / properties / checkin / description
      Previous value: -"User's check-in date, YYYY-MM-DD, if given: links then open on this stay."New value: +"User's check-in date, YYYY-MM-DD (e.g. 2027-03-12), if given: links then open on this stay."
    • changedInput schema / properties / checkout / description
      Previous value: -"Check-out date, YYYY-MM-DD."New value: +"Check-out date, YYYY-MM-DD (e.g. 2027-03-15)."
  2. Changed5 schema fields changed
    • addedInput schema / properties / adults
      Added value: +{
+  "description": "Guests per room, if given.",
+  "maximum": 8,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / checkin
      Added value: +{
+  "description": "User's check-in date, YYYY-MM-DD, if given: links then open on this stay.",
+  "type": "string"
+}
    • addedInput schema / properties / checkout
      Added value: +{
+  "description": "Check-out date, YYYY-MM-DD.",
+  "type": "string"
+}
    • addedInput schema / properties / detail
      Added value: +{
+  "description": "summary (default) or full: every scored signal with its explanation, about four times longer.",
+  "enum": [
+    "summary",
+    "full"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / focus
      Added value: +{
+  "description": "Signals the user asked about, as filter ids or names (e.g. ['quiet', 'bed', 'wifi']); always included with their reasons.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false; the description adds the practical consequences ('Read-only, no sign-in') plus a concrete cost tradeoff for detail='full' (about four times longer) and a full inventory of returned content. It stops short of describing pagination or failure behavior for an unknown hotel_id.

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 trigger is front-loaded and the return-value sentence earns its length by listing what the agent will actually see. The middle sentence is a dense run-on that would read better split, but no sentence is filler.

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?

There is no output schema, so the description carries the return-shape burden itself and does so by naming each payload component. Combined with explicit guidance on focus and detail, an agent has everything needed to call this correctly for a single-hotel lookup.

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 all six parameters are already documented and the baseline is 3. The description adds modest value beyond that: routing focus to 'what the user asked about' and quantifying detail='full' as roughly four times longer, but it adds nothing for adults, checkin, or checkout beyond 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 opens with a precise trigger ('when the user asks about one hotel') and enumerates exactly what comes back: Comfort Score breakdown, must-haves, strengths/complaints with reasons, price, city tax, link. It implicitly separates itself from search_hotels and compare_hotels by scoping to a single hotel's detail view.

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 trigger is explicit ('when the user asks about one hotel: why it scores as it does, or whether it's quiet, clean or good for sleep or work') and it tells the agent how to set focus and when to escalate to detail='full'. It doesn't name the alternatives (search_hotels for discovery, compare_hotels for multi-hotel comparison) or state when not to use it, so a small inference remains.

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

All OKstays toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources