SuperCatch

Prepare frozen drafts for internal review

supercatch_prepare_listing_submission

Freeze explicit owned DRAFT IDs, their exact versions and native readiness policy for submission to SuperCatch's internal review queue. Readiness is rechecked before every native commit. Submit an explicit frozen set of existing owned DRAFT listings that already pass SuperCatch's native readiness checks to its internal moderation queue. Does not approve or activate listings, publish to marketplaces, bypass moderation, repair blockers, change prices or stock, or select by a live search filter. A strict listing.draft.submit plan or durable per-item operation receipt. Public pages contain at most five items with whole-selection totals and a bound continuation cursor; private policy fingerprints stay on the server. Requires OAuth store:listings:drafts:submit consent. Requires separate store:listings:drafts:submit consent, an approved owned store and current EDIT_LISTINGS permission. Draft-edit, price and inventory consent do not imply submission authority. Frozen membership is limited to 100 targets; plans expire after nine minutes. Native activity provides inspection and continuation without bypassing the original grant. Preparation persists an expiring frozen manifest. Execution attempts up to five queued items through the native bulk-submit owner. Each DRAFT-to-PENDING commit and item receipt share one transaction; marketplace publication is not requested. Missing drafts, stale versions or readiness changes fail without substituting other targets. After a lost response, recover the original key or operation. A repeated execution continues only queued items; completed items are never submitted again. Unknown outcomes require reconciliation before new intent.

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": {
      "targets": [
        {
          "listing_id": "owned-draft-id",
          "expected_version": "2026-11-04T16:00:00Z"
        }
      ]
    },
    "name": "supercatch_prepare_listing_submission"
  }
}

Input Schema

Name	Required	Description	Default
`targets`	Yes	Explicit frozen set of up to 100 owned DRAFTs and exact versions to submit to SuperCatch's internal review queue. This does not approve, activate or publish listings.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

B3.4/5.0

Behavior4/5

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

The description adds substantial behavioral detail beyond the annotations: the frozen manifest expires after nine minutes, membership is limited to 100 targets, missing or stale drafts fail without substitution, and preparation requires explicit consent. Some of this transparency describes execution behavior rather than this preparation tool, which creates some noise, but the core mutation and failure semantics are well disclosed.

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 a dense wall of text with duplicated consent language ('Requires OAuth store:listings:drafts:submit consent. Requires separate store:listings:drafts:submit consent...') and includes execution details that are not relevant to a prepare tool. The purpose is front-loaded, but the overall length and repetition make it harder to scan than necessary.

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?

For a complex mutation/plan tool with annotations and an output schema, the description covers prerequisites, target limits, expiry, failure modes, and recovery guidance. The main gap is that it does not cleanly separate preparation semantics from execution semantics, leaving the agent without a crisp statement of what this call returns or when to proceed to the execute sibling.

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. The description adds meaningful semantics beyond the schema: the target set must be explicitly frozen and owned, readiness is rechecked, membership is capped at 100, and changed versions cause failure without substituting other targets. These details help the agent understand the `targets` parameter as an exact frozen set, not a search-derived selection.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence clearly says to freeze explicit owned DRAFT IDs and versions for submission to internal review. However, the description later says it will 'Submit an explicit frozen set' and describes execution behavior such as bulk-submit commits, which blurs the boundary with the sibling `supercatch_execute_listing_submission` tool. The purpose is specific but muddled by conflating preparation with execution.

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?

The description lists clear exclusions ('Does not approve or activate listings, publish to marketplaces, bypass moderation...') and prerequisites such as OAuth consent and EDIT_LISTINGS permission. It does not explicitly say when to use this preparation tool versus `supercatch_execute_listing_submission` or `supercatch_get_listing_submission_plan`, so the agent must infer the intended workflow.

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?