SuperCatch

Execute an approved import resume

supercatch_execute_import_resume

DestructiveIdempotent

Resume the exact native-web-approved import checkpoint once with a stable idempotency key. Resume one FAILED or CANCELLED CSV_IMPORT / INDIVIDUAL preloaded job no older than 30 days, with explicit AI recognition disabled and at most 100 remaining items, preserving its checkpoint, settings and reviewed items; inspect and approve the exact plan in SuperCatch first. No start-over, reprocess, bulk retry, configuration override, credential input, fee approval, USPS purchase or claim of completed import work. A strict expiring plan or durable source-to-successor receipt. A queued successor is local success only; provider results and completed processing remain unverified. Raw configuration and credentials are never returned. Requires OAuth store:imports:resume consent. Requires separate store:imports:resume consent, current EDIT_LISTINGS permission and an approved owned store. One exact source per plan. Conversational confirmation cannot replace native bound approval. Atomically creates one queued successor and native receipt, then requests worker delivery. The bounded worker processes preloaded CSV items with AI recognition disabled; external-provider, unsupported-mode and paid-AI jobs are refused. Foreign, stale, ineligible, already-retried or unapproved sources and revoked grants fail closed. Recover the original operation with its original key after a lost response; never create another intent to escape uncertainty.

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": {
      "plan_id": "import-resume-plan-id",
      "idempotency_key": "import-resume-intent-0001"
    },
    "name": "supercatch_execute_import_resume"
  }
}

Input Schema

Name	Required	Description
`plan_id`	Yes	Persisted exact plan ID returned by the prepare tool; targets and amounts cannot be replaced during execution.
`approval_ref`	No	Optional trusted approval reference for this exact actor, plan and payload. A supplied value is verified; conversational confirmation is not an approval.
`idempotency_key`	Yes	Stable client-generated key for this exact intent. Reuse it after a lost response; a different intent must use a new key.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4/5.0

Behavior5/5

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

Goes far beyond the annotations by disclosing the atomic create-successor-plus-receipt step, subsequent worker delivery, refusal of foreign/stale/ineligible/already-retried/unapproved sources, fail-closed behavior on revoked grants, and that queued != processed. It also explains the idempotent recovery path after a lost response, which no annotation conveys.

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?

Front-loaded and information-dense, but bloated: the consent requirement appears twice in near-duplicate sentences, and subjectless fragments ('A strict expiring plan or durable source-to-successor receipt.') obscure meaning. Several clauses could be merged without losing content.

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?

Covers permissions (store:imports:resume, EDIT_LISTINGS), ownership, eligibility, failure modes, and recovery, and the output schema handles return shape. A few sentences are ambiguous enough that an agent may misread what the expiring plan or receipt requirement actually demands.

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 coverage is 100%, so plan_id, approval_ref and idempotency_key are already documented. The description reinforces two semantics — one exact source per plan and that conversational confirmation is not an approval — but adds little syntax or meaning the schema does not already state.

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?

Opens with a specific verb+resource+scope ('Resume the exact native-web-approved import checkpoint once with a stable idempotency key') and narrows eligibility to FAILED/CANCELLED CSV_IMPORT / INDIVIDUAL preloaded jobs. The prepare/execute pairing is implied ('inspect and approve the exact plan in SuperCatch first') rather than naming supercatch_prepare_import_resume, so sibling differentiation is contextual rather than explicit.

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 concrete eligibility gates (state, age ≤30 days, ≤100 remaining items, AI recognition disabled) and an extensive exclusion list: no start-over, bulk retry, configuration override, credential input, fee approval, USPS purchase. The prerequisite ordering (approve the exact plan first) is stated, but the approved-plan producer is not named as a tool.

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?