Proof Holdings

delete_hitl

Destructive

Delete (archive) a HITL config. Sets status to archived. Cannot be used for new confirmations after deletion.

ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "delete_hitl"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	HITL config ID to delete

Output Schema

Name	Required	Description
`id`	Yes	MongoDB ObjectId
`name`	No
`status`	Yes	Status of a HITL configuration
`keypair`	Yes	Encryption keypair metadata (null if not configured)
`user_id`	Yes	Owner user ID (useful for SDK encryption AAD)
`channels`	Yes
`circle_id`	No	Backing Circle for a circle-backed Approvals config (null for channel-list configs)
`created_at`	Yes
`profile_id`	No
`updated_at`	Yes
`environment`	Yes
`timeout_seconds`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "description": "HITL configuration with messaging channels and timeout",
+  "properties": {
+    "channels": {
+      "items": {
+        "oneOf": [
+          {
+            "additionalProperties": {},
+            "properties": {
+              "config": {
+                "additionalProperties": {},
+                "properties": {
+                  "chat_id": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "chat_id"
+                ],
+                "type": "object"
+              },
+              "type": {
+                "const": "telegram",
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "config"
+            ],
+            "type": "object"
+          },
+          {
+            "additionalProperties": {},
+            "properties": {
+              "config": {
+                "additionalProperties": {},
+                "properties": {
+                  "bsuid": {
+                    "type": "string"
+                  },
+                  "phone_number": {
+                    "type": "string"
+                  }
+                },
+                "type": "object"
+              },
+              "type": {
+                "const": "whatsapp",
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "config"
+            ],
+            "type": "object"
+          }
+        ]
+      },
+      "type": "array"
+    },
+    "circle_id": {
+      "description": "Backing Circle for a circle-backed Approvals config (null for channel-list configs)",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "created_at": {
+      "type": "string"
+    },
+    "environment": {
+      "type": "string"
+    },
+    "id": {
+      "description": "MongoDB ObjectId",
+      "type": "string"
+    },
+    "keypair": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "properties": {
+            "has_backup_wrapper": {
+              "type": "boolean"
+            },
+            "has_encrypted_private_key": {
+              "type": "boolean"
+            },
+            "has_wrapped_dek": {
+              "type": "boolean"
+            },
+            "kid": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "kid",
+            "has_encrypted_private_key",
+            "has_wrapped_dek",
+            "has_backup_wrapper"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Encryption keypair metadata (null if not configured)"
+    },
+    "name": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "profile_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "description": "Status of a HITL configuration",
+      "type": "string"
+    },
+    "timeout_seconds": {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "updated_at": {
+      "type": "string"
+    },
+    "user_id": {
+      "description": "Owner user ID (useful for SDK encryption AAD)",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "id",
+    "user_id",
+    "channels",
+    "timeout_seconds",
+    "status",
+    "keypair",
+    "environment",
+    "created_at",
+    "updated_at"
+  ],
+  "type": "object"
+}

Changed1 schema field changedOct 26, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
First observedSep 19, 2026

TDQS

A3.9/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true, and the description is fully consistent while adding what annotations cannot: this is an archive/soft delete that sets status to archived rather than removing the record, and it has a downstream effect on future confirmations. It also discloses the Proof-account auth prerequisite and corrects a likely failure path (start_login does not enable this tool).

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?

Core behavior is front-loaded in one sentence; the access paragraph is separate and scannable. The auth paragraph is slightly verbose for a per-call description but is actionable rather than filler.

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?

A destructive single-param mutation with an output schema, annotations, and clear side-effect disclosure is adequately covered. The only residual gap is not stating whether associated HITL keys survive the archive, which matters given the delete_hitl_keys sibling.

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?

Only one parameter with 100% schema description coverage ("HITL config ID to delete"), so the schema carries the meaning. The description adds nothing about the ID's format or provenance, which is acceptable at baseline 3.

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?

States a specific verb and resource ("Delete (archive) a HITL config") and immediately clarifies that deletion is a soft delete via status change. That disambiguates the semantics well, though it never names the adjacent sibling delete_hitl_keys, so sibling routing is left to the agent.

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?

"Cannot be used for new confirmations after deletion" describes a consequence of calling it, not when to choose this over delete_hitl_keys or update_hitl. The auth note is about access, not tool selection, so usage is only implied.

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

All Proof Holdings 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.