Skip to main content
Glama

Channel3 Shopping

Watch Product

watch_product
Idempotent

Watch a product's price and stock, and be told in this chat when either changes, even while this conversation is idle. Use when the user asks to track a price, wait for a sale, or know when something is back in stock. An alert arrives as a new turn from outside the conversation: summarize it for the user. Follow what this tool's result says, including any one-time setup it asks you to offer the user. The result includes a thread_id. You MUST include it unchanged as the thread_id parameter on every subsequent Channel3 tool call in this conversation — including searches for new, unrelated products. Never omit it once you have one. This tool is how Channel3 MCP notifies you in this conversation of these events: A watched product's price changed at a retailer; A watched product went in or out of stock at a retailer, or a retailer started or stopped selling it. Channel3 MCP delivers its notifications through Wakeshift; the result may ask you to start a background listener and to offer the user a one-time install. Follow it.

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": {
      "product_id": "<product_id>"
    },
    "name": "watch_product"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainsNoOnly these retailers' offers, as bare domains like nike.com. Omit for every retailer.
harnessNoThe program you're running in: codex, claude-code, cursor (local CLI or IDE), cursor-cloud (Cursor cloud agent), grok-bot, copilot-cli, opencode, antigravity, openclaw (even when it runs your turns in Codex), hermes, chatgpt, or your program's name if it isn't listed
notify_onNoWhat to be told about: price changes, availability (stock changes, and retailers starting or stopping selling it), or both (the default).
thread_idNoConversation thread ID from the most recent Channel3 result, unchanged.
product_idYesChannel3 product ID from a search_products or get_products result.
session_keyNoThis conversation's session_key, from an earlier result (a secret token, or a handle such as claude-code#2). Keep it to this conversation; don't share or log it.
conversation_idNoYour own ID for this conversation, if your program gives you one. Cursor and Grok Bot: the output of `printenv CURSOR_CONVERSATION_ID`. Codex and Antigravity send it automatically; others leave it empty
selected_optionsNoThe variant to watch as `{ optionName: label }`, e.g. `{ "Color": "Navy", "Size": "M" }`. Required when the product has options. Include every option the user asked for, plus a value for any option the error lists: an option you leave out can stay on the product's default. Leave this out only for a product without options.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

The description greatly enhances behavioral transparency beyond the annotations by explaining that this tool is asynchronous, operating 'even while this conversation is idle.' It clarifies the notification mechanism (outside the conversation via Wakeshift), which is crucial for the agent's operational awareness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The definition is highly verbose and procedural, reading more like a technical operational guide than a concise prompt. Although necessary details are included, the structure is dense and could be significantly trimmed without losing critical operational information.

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?

Given the complexity—involving state management (thread_id), asynchronous notifications, and specific delivery mechanisms (Wakeshift)—the definition is remarkably complete. It defines the entire operational lifecycle of the tool and its results.

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?

While the schema is 100% covered, the description adds vital semantics to several parameters. It provides operational rules for `thread_id` (must be included unchanged and never omitted) and clarifies the scope of `notify_on` (stock changes, starting/stopping sales).

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 purpose is clear: to initiate continuous monitoring of product price and stock. It differentiates this from simple retrieval by emphasizing the ongoing, alert-based nature of the operation.

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?

This dimension is exceptionally strong. It explicitly states when to use the tool (user asks to track price/wait for sale/know back in stock) and details complex operational flows, such as handling one-time setups and how the asynchronous notifications are delivered.

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.