Skip to main content
Glama

Aurinia — book across venues via your AI assistant

book

Books at a network venue on the user's behalf. Takes provider_id and item, which the venue interprets: doctor — item={date,time}; hostel — item={check_in,check_out,guests,promo_code?} (underscores: check_in/check_out, not 'checkin'/'checkout'; guests is an integer; a dorm bed is the default, there is no room_type). No name or contact is required: identity comes from the one-time Telegram consent. At a hostel the call returns a HOLD together with a payment_url, and the booking is finalized by payment rather than by this call; a doctor visit is free. If the user is not yet authorized at that venue the call returns linked=false with consent_url (and consent_url_native when available) instead of a booking, and the same call succeeds once the user has approved in Telegram. Authorization: one Telegram consent per venue, which also covers later calls.

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": {
      "provider_id": "<provider_id>",
      "item": "<item>"
    },
    "name": "book"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemYesBooking details, interpreted by the venue. Doctor: {date:'YYYY-MM-DD', time:'HH:MM'}. Hostel: {check_in:'YYYY-MM-DD', check_out:'YYYY-MM-DD', guests:<int>, promo_code?}. No name or contact — identity comes from the one-time Telegram consent.
provider_idYesVenue id as returned by find_providers (e.g. rudko-vertebrolog).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / item / description
      Previous value: -"Doctor: date,time. Hostel: check_in,check_out,guests,promo_code? (no contact needed — identity via Telegram consent)."New value: +"Booking details, interpreted by the venue. Doctor: {date:'YYYY-MM-DD', time:'HH:MM'}. Hostel: {check_in:'YYYY-MM-DD', check_out:'YYYY-MM-DD', guests:<int>, promo_code?}. No name or contact — identity comes from the one-time Telegram consent."
    • addedInput schema / properties / provider_id / description
      Added value: +"Venue id as returned by find_providers (e.g. rudko-vertebrolog)."
  2. Changed1 schema field changed
    • changedInput schema / properties / item / description
      Previous value: -"Doctor/spa: date,time. Hostel: check_in,check_out,guests,promo_code? (no contact needed — identity via Telegram consent)."New value: +"Doctor: date,time. Hostel: check_in,check_out,guests,promo_code? (no contact needed — identity via Telegram consent)."
  3. Changed1 schema field changed
    • changedInput schema / properties / item / description
      Previous value: -"Лікар/спа: date,time. Хостел: check_in,check_out,guests,promo_code? (контакт не потрібен — ідентичність через Telegram-згоду)."New value: +"Doctor/spa: date,time. Hostel: check_in,check_out,guests,promo_code? (no contact needed — identity via Telegram consent)."
  4. Changed1 schema field changed
    • changedInput schema / properties / item / description
      Previous value: -"Хостел вимагає guest:{name,contact}. Лікар/спа — date/time."New value: +"Лікар/спа: date,time. Хостел: check_in,check_out,guests,promo_code? (контакт не потрібен — ідентичність через Telegram-згоду)."
  5. Changed1 schema field changed
    • addedInput schema / properties / item / description
      Added value: +"Хостел вимагає guest:{name,contact}. Лікар/спа — date/time."
  6. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that hostel bookings return a HOLD plus payment_url and are finalized by payment, that doctor visits are free, and that unauthenticated calls return linked=false with consent_url/consent_url_native rather than booking. It also explains the authorization model (one Telegram consent per venue, reused for later calls), which the hints alone cannot 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?

Front-loads what the tool does and then layers venue-specific detail and auth behavior; nearly every clause carries information. It is dense and somewhat run-on (multiple parentheticals, em-dash asides), which slightly hurts scanability but not comprehension.

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 write tool with no output schema, nested object params, and a non-obvious consent flow, the description covers inputs, return shapes, failure mode, and authorization. An agent would know exactly what happens on success and on unauthorized calls.

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 already 100%, but the description adds genuinely new meaning: dorm bed is the default, there is no room_type, underscores must be check_in/check_out, guests is an integer, promo_code is optional. Some of this restates the schema, which keeps it from a 5.

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 and resource ('Books at a network venue on the user's behalf') and immediately pins down the two inputs and how each venue type interprets them. It clearly contrasts with siblings like find_providers/cancel by naming provider_id provenance and the fact that this call creates the booking.

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 clear context for when to call (acting on the user's behalf at a specific venue) and explains the consent gate, including that the same call succeeds after Telegram approval. It stops short of explicitly naming alternatives such as checking availability first or using reschedule for changes, so it is clear but not fully exclusionary.

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