Skip to main content
Glama

Add a rental to a cart

add_to_cart
Idempotent

Add one rental to a real Sky High cart for a party date, delivery ZIP and hours, and get back a cart_id. Call build_quote first if the customer has not seen the price. To add more items to the SAME party, call again with the cart_id from the first call (one cart, one delivery fee). Safe to repeat: an item already in the cart is not added twice. Added is NOT reserved: nothing is held until the customer pays at checkout. Next step: prepare_checkout with the cart_id.

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": {
      "date": "<date>",
      "zip": "<zip>"
    },
    "name": "add_to_cart"
  }
}

Input Schema

NameRequiredDescriptionDefault
zipYes5-digit delivery ZIP (selects Houston, Austin or Dallas)
dateYesParty date, YYYY-MM-DD
cart_idNoThe cart_id from an earlier add_to_cart, to add to the same cart. Leave out to start a new cart.
productNoProduct name, e.g. 'Turtle Beach water slide', when there is no product_id.
end_timeNoParty end, e.g. 18:00 or 6pm (default 4 hours after the start). The price depends on the length.
quantityNoHow many, default 1. A package whose name already lists its counts is quantity 1.
overnightNotrue = keep it overnight, picked up after 8 AM the next morning
product_idNoThe product_id from build_quote or product_info. Preferred: it books exactly that product.
start_timeNoParty start, e.g. 14:00 or 2pm (default 12:00)
operating_modeNoFor a slide or combo that can run wet or dry: how the customer wants it. Ask them. Some units charge for wet use (a misting hose); the tool reports the charge.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / operating_mode
      Added value: +{
      +  "description": "For a slide or combo that can run wet or dry: how the customer wants it. Ask them. Some units charge for wet use (a misting hose); the tool reports the charge.",
      +  "enum": [
      +    "wet",
      +    "dry"
      +  ],
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true; the description goes beyond them by specifying the idempotency granularity ('an item already in the cart is not added twice'), the critical reservation semantics ('Added is NOT reserved: nothing is held until the customer pays'), and the delivery-fee consequence of cart reuse. These are exactly the behavioral facts an agent cannot infer from the annotations.

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?

Front-loads what the tool does and what it returns, then prerequisites, reuse semantics, safety, and next step in tight sentences with no repetition. Each sentence carries a distinct, actionable fact.

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 10-parameter mutation tool with no output schema, the description still covers the prerequisite flow, the returned cart_id, the repeat-call pattern, non-reservation of inventory, and the follow-up tool. Nothing needed to call it correctly in a workflow 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 the baseline is 3, but the description adds real meaning for cart_id — reuse it to keep a single cart and single delivery fee — which the schema description does not say. It does not touch the other eight parameters, so it does not reach 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 precise verb and resource ('Add one rental to a real Sky High cart') and names the inputs that scope it (party date, delivery ZIP, hours) plus the return value (cart_id). It is immediately distinguishable from build_quote, delivery_fee, prepare_checkout and product_info.

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?

Gives explicit prerequisites ('Call build_quote first if the customer has not seen the price'), an explicit continuation rule (reuse cart_id to keep one cart and one delivery fee), and an explicit next step ('prepare_checkout with the cart_id'). Alternatives and the conditions selecting them are all named.

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