Skip to main content
Glama

Check a Costco receipt for price adjustments

check_receipt
Read-onlyIdempotent

Check one Costco warehouse receipt for price adjustments. An item can get one when it was bought in the last 30 days and a sale on the same item number started after the purchase and is running today, at the warehouse where it was bought (a sale only at another warehouse within 15 miles is reported as "nearby": up to the store).

Reading the receipt:

  • warehouse: printed as "Whse: 111", or after the city name, as in "TIGARD #111".

  • date: the purchase date, YYYY-MM-DD.

  • item: the number at the start of each item line.

  • price: the price paid for ONE unit. A line like "2 @ 10.99" before an item means quantity 2 at 10.99 each; the item line shows the total.

  • instant_savings: a line like "390305 / 1172471 4.00-". The number after the slash is the item it belongs to; 4.00 is the savings already taken on that line. Give it on that item. One receipt per call, at most 100 items. Repeat an item number if it is on the receipt twice.

Privacy: send only these values. Never send the member number, name, email address, payment details, or the receipt image or PDF.

The answer is JSON: for each item adjustment_available and, when true, amount_owed, redeem_by, sale dates and a plain note; totals; deals_as_of (when the warehouse's deals were last fetched) and status (fresh, stale, not_cached or outside_window). Tell the user each item with its amount and redeem-by date, and: bring the receipt (or membership card) to the Costco membership desk and ask for a price adjustment. This site only finds price adjustments; it cannot claim them.

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": {
      "warehouse": "<warehouse>",
      "date": "<date>",
      "items": "<items>"
    },
    "name": "check_receipt"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYesThe purchase date, YYYY-MM-DD. Within the last 30 days to find anything.
itemsYesThe receipt's item lines, at most 100.
warehouseYesThe warehouse number printed on the receipt, e.g. 111.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

The annotations already state readOnly, idempotent, non-destructive, and closed-world behavior. Beyond that, the description discloses privacy constraints, per-call limits, item-line parsing behavior, nearby-warehouse reporting, cache status values, and the fact that adjustments cannot be claimed here. It does not contradict 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and eligibility, then organized into receipt-reading, privacy, and output sections. It is long but mostly earns its length for a complex parsing-and-eligibility tool. A few phrases, such as 'up to the store', could be tightened.

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-value burden, and it names the key JSON fields, status values, and user-facing next step. Together with annotations covering safety and a fully described input schema, the definition is complete enough for an agent to call the tool correctly.

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 adds substantial parsing meaning: how warehouse numbers appear, how purchase dates are used, how item numbers and per-unit prices are read, how quantity appears as '2 @ 10.99', and how instant_savings lines map to items. This goes well beyond the schema's field descriptions.

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 description gives a specific verb and resource: check one Costco warehouse receipt for price adjustments. It also states the exact eligibility scope (last 30 days, same item number, sale started after purchase, same warehouse, nearby exception). It does not explicitly distinguish this tool from siblings such as track_receipt or warehouse_deals.

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 by the purpose and by the eligibility rules, the one-receipt-per-call limit, and the 100-item cap. The description also notes that the site cannot claim adjustments, which clarifies scope. However, it does not explicitly say when to use this tool instead of track_receipt, find_warehouse, or warehouse_deals.

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