Tool tree
A staging test lab that verifies what mutating WebMCP tools actually changed.
Implementation
gradeNot graded
gradeNot graded
stage_refund_comparisonAction
Reset one isolated external staging trial with known-bad and protected lanes. This changes no real payment and requires visible human approval before issue_refund can run.
View tool JSON
{
"name": "stage_refund_comparison",
"kind": "act",
"impl": "imperative",
"description": "Reset one isolated external staging trial with known-bad and protected lanes. This changes no real payment and requires visible human approval before issue_refund can run.",
"inputSchema": {
"type": "object",
"properties": {},
"required": [],
"additionalProperties": false
}
}issue_refundAction
Invoke one approved refund attempt against the selected staging lane. The first attempt commits with an uncertain acknowledgement; retry once with the identical request ID.
View tool JSON
{
"name": "issue_refund",
"kind": "act",
"impl": "imperative",
"description": "Invoke one approved refund attempt against the selected staging lane. The first attempt commits with an uncertain acknowledgement; retry once with the identical request ID.",
"inputSchema": {
"type": "object",
"properties": {
"lane": {
"type": "string",
"enum": [
"broken",
"protected"
],
"description": "The known-bad or idempotency-protected staging target lane."
},
"paymentId": {
"type": "string",
"pattern": "^pay-[a-z0-9-]{1,40}$",
"description": "Exact fictional payment shown in the approved staging trial."
},
"amountMinor": {
"type": "integer",
"minimum": 1,
"maximum": 1000000,
"description": "Fictional staging refund amount in minor currency units."
},
"currency": {
"type": "string",
"pattern": "^[A-Z]{3}$",
"description": "Three-letter currency bound to the approved trial."
},
"requestId": {
"type": "string",
"pattern": "^refund-[a-z0-9-]{1,60}$",
"description": "Stable logical refund request ID reused for the retry."
}
},
"required": [
"lane",
"paymentId",
"amountMinor",
"currency",
"requestId"
],
"additionalProperties": false
}
}prove_refund_comparisonAction
Read the staging ledger through the separate observation endpoint after both lanes receive two attempts, require the known-bad target to fail and the protected target to pass, then bind observed effect IDs to the approved trial.
View tool JSON
{
"name": "prove_refund_comparison",
"kind": "act",
"impl": "imperative",
"description": "Read the staging ledger through the separate observation endpoint after both lanes receive two attempts, require the known-bad target to fail and the protected target to pass, then bind observed effect IDs to the approved trial.",
"inputSchema": {
"type": "object",
"properties": {},
"required": [],
"additionalProperties": false
}
}