Skip to main content
Glama

Schedule hotel pickup

book_hotel_pickup
Destructive

Schedule a laundry pickup for a hotel guest. Creates an order without requiring a Fold account. Returns an order tracking code (FHL-XXXXXX) and a Stripe payment-setup URL. The user must visit the Stripe URL to enter their card before pickup. The card is NOT charged when scheduling — only after intake when the actual price is known.

Hotel guest pricing (current amounts: get_pricing → hotelGuestRates): wash & fold is a flat price up to a set weight, then per pound; dry cleaning is priced per garment. There is a hotel order minimum (higher when the order is booked and returned the same day) covering wash & fold and dry cleaning. A flat hotel service charge is added to every hotel order on top of the minimum, and the Express surcharge (when chosen) is also on top — neither counts toward the minimum. The response repeats the amounts that apply to this booking.

Return-time tiers: • same_day — guest must drop the bag before 9 AM Pacific. Standard same-day return (back by 8 PM), no surcharge. Covers wash & fold AND dry cleaning. • express_same_day — drop between 9 AM and 12 PM. ⚡ Express same-day (back by 8 PM tonight). Flat Express surcharge (get_pricing → hotelExpressSurcharge). • next_day — drop any time. Standard next-day return (back by 8 PM tomorrow). No surcharge. Most common choice. • flexible — 48+ hours. No surcharge.

Same-day options are not available after 12 PM Pacific time (Los Angeles / San Francisco); requests after noon are next_day or later. The server enforces these cut-offs on its own clock: a same_day request between 9 AM and noon is refused with a message to use express_same_day — confirm the Express surcharge with the guest before retrying — and any same-day request after noon is refused (use next_day). It never adds a surcharge or changes the day silently.

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": {
      "hotelPlaceId": "<hotelPlaceId>",
      "hotelName": "<hotelName>",
      "guestFirstName": "<guestFirstName>",
      "guestLastName": "<guestLastName>",
      "guestEmail": "<guestEmail>",
      "guestPhone": "<guestPhone>",
      "roomNumber": "<roomNumber>",
      "services": "<services>",
      "returnPreference": "<returnPreference>"
    },
    "name": "book_hotel_pickup"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNoOptional special instructions (e.g. "no fabric softener", "handle silk delicately").
servicesYesWhat services to perform. Most guests pick WASH_AND_FOLD.
hotelNameYesHotel display name (from search_hotels result). Required.
guestEmailYesGuest email (used for tracking + receipts)
guestPhoneYesGuest phone in E.164 format (+1XXXXXXXXXX) or US 10-digit
roomNumberYesGuest room number at the hotel
hotelPlaceIdYesGoogle Place ID for the hotel, obtained from search_hotels. Required.
guestLastNameYesGuest last name
guestFirstNameYesGuest first name
idempotencyKeyNoOPTIONAL — pass a unique identifier (UUID recommended) to make this call safe to retry. If we have already seen this key, we return the EXISTING order code instead of creating a duplicate. Highly recommended for production agents that may retry on network errors.
returnPreferenceYesWhen the guest wants the laundry back. same_day requires drop-off before 9 AM (no surcharge). express_same_day works for drop-off between 9 AM and 12 PM noon (+$30 surcharge, back by 8 PM tonight). next_day is the typical choice — drop any time, back by 8 PM tomorrow (no surcharge). flexible = 48hr+. Pick same_day or express_same_day only if local time clearly allows it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / returnPreference / description
      Previous value: -"When the guest wants the laundry back. same_day requires drop-off before 9 AM (no surcharge). express_same_day works for drop-off between 9 AM and 12 PM noon (+$30 surcharge, back by 7 PM tonight). next_day is the typical choice — drop any time, back by 7 PM tomorrow (no surcharge). flexible = 48hr+. Pick same_day or express_same_day only if local time clearly allows it."New value: +"When the guest wants the laundry back. same_day requires drop-off before 9 AM (no surcharge). express_same_day works for drop-off between 9 AM and 12 PM noon (+$30 surcharge, back by 8 PM tonight). next_day is the typical choice — drop any time, back by 8 PM tomorrow (no surcharge). flexible = 48hr+. Pick same_day or express_same_day only if local time clearly allows it."
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations declare this is a mutating, open-world, non-idempotent operation, and the description goes well past that: it discloses that an order is created with no account, that the response carries an FHL-XXXXXX tracking code and a Stripe setup URL, and that the card is not charged until intake when real pricing is known. It also documents server-enforced cutoff behavior — a 9 AM–noon same_day request is refused with a redirect to express_same_day, and post-noon requests are refused outright — and states the server never silently adds a surcharge or changes the day.

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 first paragraph is front-loaded with the highest-value facts (order creation, no account, payment URL, deferred charge), and the tier bullets are scannable. It runs long and the pricing/minimum paragraph overlaps territory owned by get_pricing, though it does correctly route the agent there for current amounts.

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?

With 11 parameters (9 required), no output schema, and an open-world destructive annotation, the description supplies everything needed: the return shape (tracking code, Stripe URL, repeated amounts), payment timing, tier cutoffs, and refusal semantics. Nothing an agent would need before calling is missing.

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 100%, so baseline is 3, and the description earns above that by adding real meaning for returnPreference (drop-time windows, which services each tier covers, surcharge behavior) and for services (wash & fold is flat-then-per-pound, dry cleaning per garment). It does not add anything for the identity, hotel, or room parameters, which is the remaining gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence names a specific verb and resource ("Schedule a laundry pickup for a hotel guest") plus the key scope fact that no Fold account is required. However, it never distinguishes this from the near-identically named sibling book_for_hotel_guest, so an agent facing both still has to guess which one is which.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: "for a hotel guest" and "without requiring a Fold account" suggest this is the path for guests lacking an account, versus book_my_pickup or book_residential_pickup. There is no explicit when-to-use/when-not sentence and no named alternative, so routing must be inferred.

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