Skip to main content
Glama

Email the user price-adjustment alerts for a Costco receipt (they confirm by email)

track_receipt

Sign the user up for 30 days of email alerts on one Costco receipt: the site emails them when something on it goes on sale, the same as forwarding the receipt to the site. Use it ONLY when the user has asked for ongoing alerts and has given you their email address themselves; never guess or look up an address.

The site emails that address a link to confirm. Nothing is saved under the address until its owner opens that email and presses Confirm; the link lasts 7 days, and receipts not confirmed by then are deleted. Tell the user to open the email from couponpriceadjustment.com and confirm. One confirmation covers every receipt waiting for the address, so several receipts can be sent in a row (at most 10 waiting; at most 3 confirmation emails per address a day).

Read the receipt as for check_receipt (warehouse, date, items with price per unit, quantity and instant savings), and the purchase must be in the last 30 days. Optionally give each item's name as printed on the receipt (plain text, at most 60 characters, shown only to the confirmed owner) and the register transaction number ("Trn: 391"), which lets the site recognise a receipt already on file.

Unlike the other tools, this stores what it is sent: the email address and the receipt's warehouse, date, items, prices and quantities, as forwarding a receipt does. Never send the member number, payment details or the receipt image. The user can delete everything with the link in any email from the site. It does not check the receipt: call check_receipt for today's answer.

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": {
      "email": "<email>",
      "warehouse": "<warehouse>",
      "date": "<date>",
      "items": "<items>"
    },
    "name": "track_receipt"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYesThe purchase date, YYYY-MM-DD, within the last 30 days.
emailYesThe email address the user gave you for the alerts. Never guess one.
itemsYesThe receipt's item lines, at most 100.
warehouseYesThe warehouse number printed on the receipt, e.g. 111.
transactionNoThe register transaction number printed as "Trn: 391". Optional; lets the site recognise a receipt already on file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes far beyond by disclosing the double-opt-in flow, that nothing persists until the owner clicks Confirm, the 7-day link lifetime, deletion of unconfirmed receipts, and concrete rate limits (10 waiting, 3 confirmation emails per address per day). It also states exactly which data is stored and which must never be sent (member number, payment details, image), plus how the user can delete everything.

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?

Purpose and the hard eligibility rule are front-loaded, then confirmation mechanics, then data-handling. Nearly every sentence carries operational content, though a few phrases are slightly redundant (the 'same as forwarding the receipt to the site' aside, and the 30-day window stated twice).

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 no output schema, the description still tells the agent what happens after the call: a confirmation email goes out, nothing is stored until confirmed, and the agent must instruct the user to open the email. Combined with the data-retention and prohibition notes, nothing an agent needs in order to call this correctly 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 genuinely new meaning: the 'name' field is shown only to the confirmed owner, and 'transaction' exists so the site can recognise a receipt already on file. It also restates the 30-day window for 'date', which the schema already covers, so it is an increment rather than a full elaboration.

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 first clause names the specific action and scope: 'Sign the user up for 30 days of email alerts on one Costco receipt'. It also explicitly separates this tool from a sibling ('It does not check the receipt: call check_receipt for today's answer'), so an agent can route without opening the schema.

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?

It gives an explicit positive condition (user asked for ongoing alerts and supplied their own email), an explicit prohibition ('never guess or look up an address'), an alternative for the non-alert case (check_receipt), and an eligibility constraint (purchase within 30 days). That is when-to-use, when-not-to-use and alternatives in one place.

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