SuperCatch

Prepare automatic repricing changes

supercatch_preview_auto_repricing

Read-onlyIdempotent

Preview changes to ongoing repricing for the connected seller's cards. Use to review recurring behavior; automationMode is required and direction must be ANY, independently of one-time price direction. One-time price changes and marketplace exports are outside this action. Returns current listing modes, store cadence, eligible rows and a website review URL; nextCursor continues the same selection. Requires OAuth store:read consent. The connected account must own an approved store. Read-only. Website confirmation can change store-wide strategy and selected-card enrollment; this preview changes neither. Missing automationMode, non-ANY direction and malformed cursors return tool errors; no settings are changed.

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": {
      "cardType": "ALL",
      "direction": "ANY",
      "automationMode": "RECOMMEND_ONLY"
    },
    "name": "supercatch_preview_auto_repricing"
  }
}

Input Schema

Name	Required	Description	Default
`cursor`	No	Continue with nextCursor from the previous page, keeping the same selection.
`cardType`	No	Review RAW, graded/authenticated, or all active in-stock card copies in the connected store.	ALL
`strategy`	No	AT_MARKET, PREMIUM (above market), or MOVE_FAST. Omit to use the existing store strategy. Confirmed automation uses this as store-wide strategy.
`direction`	No	Filter one-time price changes. Ongoing repricing requires ANY; publishing includes all displayed cards.	ANY
`integrationId`	No	Choose an enabled connection ID returned in publishing.targets for this store. The seller confirms the exact account before a normal export job is queued.
`automationMode`	No	Prepare OFF, recommendations, or automatically applied ongoing repricing. Does not change settings until confirmed in SuperCatch.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond readOnlyHint/idempotent hints it discloses the OAuth scope (store:read), the approved-store ownership prerequisite, the specific error triggers (missing automationMode, non-ANY direction, malformed cursors), and the crucial boundary that website confirmation can change store-wide strategy and enrollment while this preview changes neither. It also describes what the response contains, which annotations cannot convey.

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?

Front-loaded with purpose and exclusions before prerequisites and error behavior, and nearly every clause carries operational information. It is dense and semicolon-chained, and 'Read-only' plus 'no settings are changed' are somewhat redundant with each other, but there is no filler.

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?

For a 6-parameter tool with no output schema, the description covers the return payload (current listing modes, store cadence, eligible rows, website review URL, nextCursor), auth and store prerequisites, and failure modes. An agent has enough to call it correctly and interpret the result without further documentation.

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 real meaning: automationMode is treated as required despite appearing in no required list, direction must be ANY regardless of the one-time direction filter, and nextCursor re-applies the same selection. That said, the claim 'automationMode is required' conflicts with the schema's empty required array, which could mislead an agent.

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?

States a specific verb and resource: 'Preview changes to ongoing repricing for the connected seller's cards.' It immediately scopes itself against adjacent work by declaring 'One-time price changes and marketplace exports are outside this action,' so an agent can separate it from supercatch_prepare_price_changes and supercatch_preview_marketplace_publish without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear usage frame ('Use to review recurring behavior') and explicit exclusions for one-time price changes and marketplace exports, plus a hard precondition that direction must be ANY. It does not name the specific sibling prepare/execute tools that would be the alternative, so routing across the ~50 siblings still requires inference.

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?