Checkout Page

list_coupons

Read-only

Retrieve a paginated list of discount coupons on your Checkout Page account. This is the only way to discover a coupon ID — take the id from here to use update_coupon.

search is a case-insensitive contains match on the coupon's label and code, so it answers "is there already a coupon for X?" before you create a duplicate with create_coupon.

Reading a coupon: the discount is either percentOff (a percentage) or amountOff (a flat amount in the smallest currency unit, paired with currency) — never both. duration is once, repeating (for durationInMonths), or forever. timesRedeemed counts redemptions so far, against maxRedemptions when one is set.

Whether a coupon actually works right now depends on several fields together, and there is no single "active" flag: deleted: true means soft deleted and dead; redeemBy in the past means expired; timesRedeemed >= maxRedemptions means exhausted. Check all three before telling a merchant a coupon is live. Soft-deleted coupons are returned by this tool — they are not filtered out.

Scoping: pageIds limits the coupon to specific pages and ticketTypeIds to specific ticket types. Empty or absent means the coupon is valid everywhere. These are IDs only — this tool does not resolve them to page or event names.

No filters beyond search. There is no way to filter by deleted, expiry, redemption count, or scope server-side. Page through and inspect those fields.

Coupons are returned sorted newest-first. Use cursor-based pagination (starting_after / ending_before) to page through large result sets. starting_after and ending_before cannot be used simultaneously. Max limit is 100, default is 10.

This tool is read-only. Use create_coupon to add one and update_coupon to change or soft delete one. A coupon's discount (code, amountOff, percentOff, currency, duration) can never be changed after creation.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Number of records per page (integer, max 100, default 10).
`search`	No	Case-insensitive contains match against the coupon's label and code. Searching '10off' matches the code `10OFF`; searching 'summer' matches the label 'Summer sale'. There is no filter for redemption count, expiry, or deleted status — page through and inspect those fields instead.
`ending_before`	No	Cursor-based pagination. Pass a record `id` to return results before it. Cannot be used with `starting_after`.
`starting_after`	No	Cursor-based pagination. Pass a record `id` to return results after it. Cannot be used with `ending_before`.

Output Schema

TableJSON Schema

Name	Required	Description
`data`	Yes
`total`	Yes	Total number of records matching the query across all pages.
`has_more`	Yes	Whether more records exist beyond the current page.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the readOnlyHint annotation: soft-deleted coupons are returned and not filtered out, there is no single 'active' flag (deleted/redeemBy/timesRedeemed+maxRedemptions must be checked together), sorting is newest-first, pageIds/ticketTypeIds are IDs not resolved names, and discount fields are immutable after creation. This is exactly the operating context an agent needs.

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?

Bold mini-headers (Reading a coupon, Scoping, No filters, etc.) keep a long description scannable, and the most important constraint (only ID-discovery path) is front-loaded. Some pagination and limit details are restated from the schema, which is the only minor redundancy.

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?

An output schema exists, so return mechanics need not be explained, yet the description still decodes coupon field semantics (percentOff vs amountOff+currency, duration variants, redemption counters) and liveness rules — everything an agent needs to interpret results and act correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so limit, search, starting_after, and ending_before are already fully documented in the schema, including the max-100/default-10 and mutual-exclusion rules the description repeats. The description adds only a small increment: framing search as a duplicate-check and reiterating the lack of other filters. Baseline 3 applies.

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?

Opens with a specific verb+resource ('Retrieve a paginated list of discount coupons on your Checkout Page account') and immediately distinguishes itself from siblings by noting it is 'the only way to discover a coupon ID' and naming create_coupon/update_coupon as the alternatives. An agent can route without opening any 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?

Explicit when-to-use: it is the sole ID-discovery path, it feeds update_coupon, and its search answers 'is there already a coupon for X?' before calling create_coupon. It also states when-not: no server-side filtering by deleted/expiry/redemption/scope, so page through instead. Nothing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Checkout Page tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?