SuperCatch

Execute one approved support message

supercatch_execute_support_operation

Idempotent

Commit one exact support case or public reply approved in SuperCatch. Open a support case or append a public reply to an owned case. Inspect the exact text, store audience and separate notification policy in SuperCatch before execution. No internal note, arbitrary recipient, attachment upload, staff action, refund, payment, inventory change, order change or authority to another workflow. A strict reviewed plan or durable operation receipt. Local commit, in-app notification and email submission have separate outcomes. Provider acceptance does not prove email delivery. Private routing and original keys are excluded. Requires OAuth account:support:write consent. Requires separate account:support:write consent and the current account's original connection. Account read, support read, store membership and staff privileges do not substitute for ownership or native bound approval. Atomically commits the reviewed native case or reply, required in-app notification and original-key receipt; then claims at most one frozen reviewed email attempt when native policy permits it. Foreign, changed, unapproved or expired reviews and revoked grants fail closed. After uncertainty inspect the original receipt and keep the original plan and key; an unknown email attempt must never be resent.

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": "reviewed-support-plan-id",
      "idempotency_key": "support-intent-stable-original-key"
    },
    "name": "supercatch_execute_support_operation"
  }
}

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 7, 2026

TDQS

A3.9/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, but the description goes well beyond them: it discloses non-atomic-looking multi-channel outcomes ('local commit, in-app notification and email submission have separate outcomes'), warns that 'provider acceptance does not prove email delivery', and defines fail-closed conditions for foreign, changed, unapproved or expired reviews and revoked grants. It also states the critical retry rule that an unknown email attempt must never be resent. This is meaningful behavior the annotations cannot express, and nothing contradicts them.

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 stream of terse fragments rather than front-loaded prose, mixing purpose, constraints, auth requirements, atomicity and recovery in one paragraph. There is visible redundancy ('Requires OAuth account:support:write consent. Requires separate account:support:write consent...'), and a sentence about inspecting text and storing audience appears to describe the prepare step rather than this tool, which muddies rather than clarifies. Sizeable editing would materially improve it.

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 mutation tool with an output schema and rich annotations, the description supplies the missing pieces an agent needs: consent requirements, connection/ownership requirements, partial-failure semantics and post-failure recovery. Nothing essential about invocation is absent. It loses a point only because the density makes some of that context hard to extract reliably.

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 each parameter is already documented in the schema, including the plan_id immutability and idempotency_key reuse rule. The description reinforces intent by saying to keep 'the original plan and key' after uncertainty, which slightly strengthens the schema's guidance but adds no syntax or format detail. A baseline 3 is appropriate when the schema does the explanatory work.

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 opening states a specific verb and resource: 'Commit one exact support case or public reply approved in SuperCatch', then narrows the two supported operations (open a case, append a public reply to an owned case). This distinguishes it from the prepare_support_case / prepare_support_reply siblings by framing it as the commit step against a reviewed plan. It falls short of 5 because the purpose is buried in a dense run-on sentence rather than stated once cleanly.

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?

It names the precondition clearly ('A strict reviewed plan or durable operation receipt') and lists explicit exclusions: no internal note, arbitrary recipient, attachment, staff action, refund, payment, inventory or order change. It also points to recovery behavior after failure ('inspect the original receipt'), which routes the agent to the operation-inspection sibling. It never explicitly names prepare_support_case or get_support_operation, so the routing is inferred rather than stated.

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?