Skip to main content
Glama

GotCashback

by com.gotcashback

Set a store alert

set_store_alert
Idempotent

Creates or updates an alert that emails the signed-in user when a store's cashback rate or gift card discount reaches the threshold percent or higher. Use it for 'alert me when Nike cashback hits 10%' or 'tell me when Target gift cards are 15% off'. Re-saving an existing alert updates its threshold and re-arms it. At most 10 active alerts per user. Needs the store_id: take it from an earlier result, or find it with get_stores_by_name (optionally with country_code). Requires OAuth sign-in with a GotCashback account and the 'alerts' scope; anonymous callers are prompted to authorize.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
store_idYesGotCashback's numeric store_id, taken from an earlier result (a store, cashback rate, gift card, deals, favorites or alerts response). If you only have a store name, use the by-name tool instead.
alert_typeYesAlert type: 'cashback' (fires on the store's best cashback rate) or 'gift_card' (fires on the store's best gift card discount). Use the alert_type value from get_my_alerts as-is.
threshold_percentYesFire when the rate/discount reaches this percent or higher (greater than 0, at most 100), e.g. 10 for 10%

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / properties / alert_type / description
      Previous value: -"Alert type: 'cashback' (fires on the store's best cashback rate) or 'gift_card' (fires on the store's best gift card discount)"New value: +"Alert type: 'cashback' (fires on the store's best cashback rate) or 'gift_card' (fires on the store's best gift card discount). Use the alert_type value from get_my_alerts as-is."
    • addedInput schema / properties / alert_type / enum
      Added value: +[
+  "gift_card",
+  "cashback"
+]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

The description adds substantial behavior beyond the annotations: it emails the signed-in user, re-saving updates the threshold and re-arms the alert, and there is a 10-alert limit. It also explains the auth flow, including that anonymous callers are prompted to authorize. This does not contradict the idempotentHint=true annotation, since updating an existing alert is idempotent.

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?

Every sentence in the description earns its place: core behavior, usage examples, update semantics, limits, store_id sourcing, and auth requirements. It is front-loaded with the primary function and remains compact despite covering many important operational details.

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?

The description is complete for an agent to select and invoke this tool correctly: it explains what the tool does, how to obtain required inputs, behavioral limits, and auth prerequisites. No output schema is present, but the description provides enough context for successful use.

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%, and the schema already documents store_id, alert_type, and threshold_percent with clear meaning. The description reinforces these with examples but does not add significant new parameter-level detail beyond what the schema provides, so the baseline of 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?

The description opens with a specific verb and resource: 'Creates or updates an alert that emails the signed-in user.' It clearly distinguishes itself from sibling alert tools like get_my_alerts and remove_store_alert by focusing on creation/update semantics.

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 concrete use examples ('alert me when Nike cashback hits 10%') and explicitly directs users to get_stores_by_name when they need a store_id. It also states the OAuth/scope requirement, which is critical when deciding whether this tool can be used in an anonymous context.

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

All GotCashback toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation4/5

Most tools target a clearly distinct resource and action, and the descriptions carefully cross-reference when to use each one. The main risk is the similar get_stores_by_name, get_cashback_rates_by_store_name, and get_gift_cards_by_store_name names, though their descriptions do a good job of separating identity, cashback rates, and gift cards.

Naming Consistency4/5

The naming follows a mostly consistent get_<resource>_by_<selector> pattern with clear verb prefixes for mutations like set, remove, and toggle. Minor inconsistencies exist, such as get_portal_by_id (singular) versus get_portals_by_name (plural), and the get_my_* cluster for account tools.

Tool Count4/5

Eighteen tools is slightly above the ideal 3-15 range, but the count is justified by the breadth of the domain: store comparison, brand and category deals, gift cards, portals, countries, and user account features. Each tool has a distinct purpose, so the set does not feel genuinely bloated.

Completeness4/5

The tool surface covers the main workflows well: finding cashback by store, brand, or category, comparing gift cards and portls, browsing countries and stores, and managing favorites, alrts, and profile. Minor gaps exist, such as no direct way to rank all stores in a country by cashback rate without per-store lookups, but agents can work around these.

Resources