ExitProof

Build exit pack

build_exit_pack

Build a bounded cancellation/refund action pack from an existing actionable Exit Manifest after manifest access and actionability preflight succeed. Use when you already have manifest_id plus access_token and need next-step instructions, deadlines, an evidence checklist, a suggested request, sources, and limitations; use get_exit_manifest for retrieval only, or check_reversibility then create_exit_manifest when no manifest exists. This $1.00 MPP operation can charge but never contacts the merchant, executes a cancellation, files a chargeback, or guarantees success. Invalid credentials or a non-actionable manifest are rejected before payment; retrying with the same settled payment credential avoids a second settlement, but generatedAt and deadlineStatus can reflect the current time.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`manifest_id`	Yes	Unguessable Exit Manifest identifier returned by create_exit_manifest. It starts with xm_ followed by 32 lowercase hexadecimal characters.
`access_token`	Yes	Secret bearer token returned by create_exit_manifest or deterministic settlement recovery. Required with manifest_id; treat it like a credential and do not log or expose it.

Output Schema

TableJSON Schema

Name	Required	Description
`steps`	Yes	Ordered bounded next steps for pursuing cancellation or refund.
`sources`	Yes	Recorded source references supporting the action pack.
`currency`	No	Currency associated with recorded monetary values.
`exitRoute`	Yes	Recorded cancellation/refund route or cited-source route to follow.
`assessment`	Yes	Reversibility assessment preserved by the manifest.
`manifestId`	Yes	Manifest used to build this action pack.
`generatedAt`	Yes	Timestamp when the action pack was generated.
`limitations`	Yes	Boundaries and caveats; ExitProof does not execute the exit or guarantee success.
`actionability`	Yes	Why the stored manifest is actionable and which exit route is established.
`prerequisites`	Yes	Checks to complete before acting on the exit plan.
`schemaVersion`	Yes	Exit-pack response schema version.
`deadlineStatus`	Yes	Current status of the recorded exit deadline at generation time.
`reversibleUntil`	No	Recorded exit deadline when established.
`suggestedRequest`	Yes	Suggested message the user or agent can adapt when requesting cancellation/refund.
`evidenceChecklist`	Yes	Evidence to retain while pursuing the exit.
`maximumStatedLossMinor`	No	Maximum stated loss in minor currency units when established.
`unresolvedLossExposure`	No	True when the recorded evidence does not establish a complete maximum loss.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 21, 2026

addedInput schema / description

Added value: +"Credentials for one previously created Exit Manifest. Both values are required together and are returned by create_exit_manifest or settlement recovery."

addedInput schema / properties / access_token / description

Added value: +"Secret bearer token returned by create_exit_manifest or deterministic settlement recovery. Required with manifest_id; treat it like a credential and do not log or expose it."

addedInput schema / properties / manifest_id / description

Added value: +"Unguessable Exit Manifest identifier returned by create_exit_manifest. It starts with xm_ followed by 32 lowercase hexadecimal characters."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Bounded action pack derived from an actionable Exit Manifest.",
+  "properties": {
+    "actionability": {
+      "additionalProperties": true,
+      "description": "Why the stored manifest is actionable and which exit route is established.",
+      "type": "object"
+    },
+    "assessment": {
+      "description": "Reversibility assessment preserved by the manifest.",
+      "type": "string"
+    },
+    "currency": {
+      "description": "Currency associated with recorded monetary values.",
+      "type": "string"
+    },
+    "deadlineStatus": {
+      "description": "Current status of the recorded exit deadline at generation time.",
+      "enum": [
+        "open",
+        "passed",
+        "not_established"
+      ],
+      "type": "string"
+    },
+    "evidenceChecklist": {
+      "description": "Evidence to retain while pursuing the exit.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "exitRoute": {
+      "additionalProperties": true,
+      "description": "Recorded cancellation/refund route or cited-source route to follow.",
+      "type": "object"
+    },
+    "generatedAt": {
+      "description": "Timestamp when the action pack was generated.",
+      "type": "string"
+    },
+    "limitations": {
+      "description": "Boundaries and caveats; ExitProof does not execute the exit or guarantee success.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "manifestId": {
+      "description": "Manifest used to build this action pack.",
+      "type": "string"
+    },
+    "maximumStatedLossMinor": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Maximum stated loss in minor currency units when established."
+    },
+    "prerequisites": {
+      "description": "Checks to complete before acting on the exit plan.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "reversibleUntil": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Recorded exit deadline when established."
+    },
+    "schemaVersion": {
+      "const": "exitproof-exit-pack.v1",
+      "description": "Exit-pack response schema version."
+    },
+    "sources": {
+      "description": "Recorded source references supporting the action pack.",
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "steps": {
+      "description": "Ordered bounded next steps for pursuing cancellation or refund.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "suggestedRequest": {
+      "description": "Suggested message the user or agent can adapt when requesting cancellation/refund.",
+      "type": "string"
+    },
+    "unresolvedLossExposure": {
+      "description": "True when the recorded evidence does not establish a complete maximum loss.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "schemaVersion",
+    "manifestId",
+    "generatedAt",
+    "assessment",
+    "actionability",
+    "exitRoute",
+    "prerequisites",
+    "deadlineStatus",
+    "steps",
+    "suggestedRequest",
+    "evidenceChecklist",
+    "sources",
+    "limitations"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedSep 21, 2026
- addedInput schema / properties / access_token / pattern
```
Added value: +"^xp_[A-Za-z0-9_-]{20,}$"
```
- addedInput schema / properties / manifest_id / pattern
```
Added value: +"^xm_[a-f0-9]{32}$"
```
First observedSep 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description adds substantial behavioral context beyond the annotations: this is a paid operation ('$1.00 MPP operation can charge'), it never contacts the merchant, executes a cancellation, files a chargeback, or guarantees success. It also explains preflight rejection before payment and the nuanced retry behavior, which is critical for correct invocation.

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?

The description is dense and entirely relevant, front-loading purpose and usage before caveats. It is somewhat long and has minor redundancy (preflight rejection is mentioned twice), but every sentence contributes useful operational information.

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 2-parameter tool with an output schema, the description covers when to use, when not to use, billing, safety boundaries, failure handling, retry behavior, and time-sensitive output fields. Nothing essential is missing for an agent to invoke it correctly.

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?

The input schema already provides 100% coverage for both parameters, including patterns, provenance, and security warnings. The description mentions needing manifest_id and access_token, but adds no meaning beyond what the schema already conveys; the baseline of 3 applies due to high schema coverage.

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?

The description uses a specific verb ('Build') and identifies a concrete resource ('bounded cancellation/refund action pack from an existing actionable Exit Manifest'). It clearly distinguishes itself from siblings by stating what get_exit_manifest is for ('retrieval only') and what to do when no manifest exists.

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

Usage Guidelines5/5

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

Explicitly states when to use the tool: 'when you already have manifest_id plus access_token and need next-step instructions...'. It also names alternatives and their conditions: 'use get_exit_manifest for retrieval only, or check_reversibility then create_exit_manifest when no manifest exists.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All ExitProof 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?