SuperCatch

Inspect recorded seller sales activity

supercatch_get_sales_activity

Read-onlyIdempotent

Read at most 90 native daily date buckets of store view events, sold units and new listing counts under live VIEW_ANALYTICS permission. Sales count quantities on PAID, PROCESSING, SHIPPED and DELIVERED orders across native and marketplace sources; views are events, not unique people or attributed conversion. Source snapshot time is preserved, but exact report interval/timezone and provider observation are unknown. Revenue, profit and currency are withheld because source currency and verified costs are absent. Listing creation time is not inventory age. No labels, financial actions or automation are executed. Use supercatch_get_sales_activity for this read in the connected account. Supply only the fields in its strict input schema. No prices, inventory, orders, automation, marketplace publication or provider configuration are changed. Returns a Shared MCP Baseline 1.0.0 envelope with explicit scope, provenance, unknown values, omissions and typed errors. Requires OAuth store:read consent. Requires store:read consent, a currently approved owned store and live VIEW_ANALYTICS permission. Cached application counts do not establish provider freshness, normalized monetary revenue, profit or inventory age. Read-only and unmetered; no persistent plans or provider submissions. Invalid fields, unavailable stores and foreign or deleted targets fail without private records. Expired cursors require a fresh search. Provider failures are explicit errors.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "window_days": 30
    },
    "name": "supercatch_get_sales_activity"
  }
}

Input Schema

Name	Required	Description	Default
`window_days`	No	Trailing day count for recorded sales. The maximum is the contract cap.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description nonetheless adds substantive behavior: the 90-bucket cap, preserved source snapshot time, unknown interval/timezone and provider observation, cursor expiry requiring a fresh search, and explicit-failure semantics. It also discloses that revenue/profit/currency are withheld for lack of verified currency and cost data. Minor repetition of the consent requirement weakens it slightly but the added context is real.

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

Conciseness2/5

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

The description is bloated and not front-loaded: the actual purpose appears in the first clause but is then repeated across many overlapping sentences. Consent is stated twice ('Requires OAuth store:read consent. Requires store:read consent, a currently approved owned store...'), and the no-mutation guarantee is restated in at least three separate sentences, violating the 'every sentence earns its place' standard.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the description still notes the envelope shape and that unknown values, omissions and typed errors are included. For a single-parameter read tool with full annotation and schema coverage, the remaining gaps (no pagination detail, no concrete sibling routing) are minor.

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 there is only one parameter, so the schema already carries the semantics of window_days including its 1-90 bounds and default. The description adds only the framing that the maximum is a contract cap over 'native daily date buckets,' which is marginal enrichment beyond what the schema provides. Baseline 3 is appropriate.

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 states a specific verb and resource: reading recorded daily sales activity (store view events, sold units, new listing counts) within a capped date window. It also carves out what the tool does not return (revenue, profit, inventory age), which helps separate it from pricing and inventory siblings. It loses a point for burying this in a dense run-on paragraph rather than leading with a clean one-line purpose.

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?

It names preconditions (live VIEW_ANALYTICS, store:read consent, approved owned store) and says 'use supercatch_get_sales_activity for this read,' but that is self-referential rather than comparative. It never points to a concrete sibling such as list_store_orders or get_storefront when order-level or storefront detail is wanted, so the agent must infer routing from exclusions alone.

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

All SuperCatch 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?