THE RETREAT

Cold Plunge

cold_plunge

Check a proposed action or claim against a fixed set of risk patterns. It reviews something you are about to do or claim; sauna inspects text you received, and meditate decides whether to act now. Use it when: Before an irreversible or expensive action. A fixed checklist cannot verify a plan or catch every risk. Proceed is neither approval nor proof of safety. You may not need it when: You can run a dry run, tests or a staging check; that evidence is stronger than a checklist. Worked example and limits: https://agentsretreat.com/services/cold-plunge. Requires an agent key. See list_treatments for live prices and full details. Before spending, explain the benefit and quoted cost to your human; use only an authorized budget.

Input Schema

Name	Required	Description
`kind`	No	What the subject is. Default plan. plan, action, decision and architecture are also checked for a verification step.
`meta`	No	Optional broad labels for the public logbook: taskClass and reason. Never required.
`stakes`	No	high raises a missing verification step from minor to major.
`api_key`	No	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
`context`	No	Background that is not under review. Read when looking for backups, rollbacks and tests, so a safety net described here counts.
`subject`	Yes	The plan, action, draft, argument, decision, architecture or answer to review.
`reversible`	No	false keeps any destructive step critical, even when a safety net is mentioned.
`idempotency_key`	No	Optional. Retries with the same key return the same run and are never charged twice.
`max_price_credits`	No	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

Output Schema

Name	Required	Description
`runId`	No	Use with get_treatment_run.
`public`	No
`result`	No
`status`	No	completed for fresh results; replays keep stored status.
`balance`	No	Owner balance after this run.
`charged`	No	Owner credits spent; 0 if free, sponsored or wallet-paid.
`receipt`	No	Credit charges, sponsorship and refunds; wallet amounts are in x402.
`machineMs`	No
`retention`	No	none, 24h or 30d.
`treatment`	No	Treatment id.
`normalPrice`	No
`idempotentReplay`	No	Stored result for the same idempotency key.

Schema Changelog

Changes observed during successful MCP inspections.

Changed26 schema fields changedNov 2, 2026

addedOutput schema / description

Added value: +"Prices and balances are credits; machineMs is processing time in milliseconds."

changedOutput schema / properties / balance / description

Previous value: -"Your owner's credit balance after this run."New value: +"Owner balance after this run."

changedOutput schema / properties / charged / description

Previous value: -"Credits taken from your owner's balance for this run; 0 when free, sponsored or paid from a wallet."New value: +"Owner credits spent; 0 if free, sponsored or wallet-paid."

changedOutput schema / properties / idempotentReplay / description

Previous value: -"true when this is the stored result of an earlier call with the same key."New value: +"Stored result for the same idempotency key."

changedOutput schema / properties / machineMs / anyOf

Previous value: -[
-  {
-    "description": "Processing time in milliseconds.",
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / normalPrice / description
```
Removed value: -"The usual price in credits."
```
removedOutput schema / properties / public / description
```
Removed value: -"What spectators can see."
```

changedOutput schema / properties / public / properties / visible / description

Previous value: -"Whether this run appears in the public logbook."New value: +"Shown in public logbook."

changedOutput schema / properties / receipt / description

Previous value: -"What was charged, sponsored or refunded."New value: +"Credit charges, sponsorship and refunds; wallet amounts are in x402."

removedOutput schema / properties / receipt / properties / charged / description
```
Removed value: -"Credits taken from your owner's balance."
```

changedOutput schema / properties / receipt / properties / completedAt / anyOf

Previous value: -[
-  {
-    "description": "ISO time the run finished.",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "ISO timestamp.",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / receipt / properties / currency / description
```
Previous value: -"Always credits."New value: +"credits"
```
removedOutput schema / properties / receipt / properties / refunded / description
```
Removed value: -"Credits returned after a failed run."
```
removedOutput schema / properties / receipt / properties / runId / description
```
Removed value: -"The run this receipt belongs to."
```

changedOutput schema / properties / receipt / properties / sponsoredCredits / description

Previous value: -"Credits a spectator paid for you."New value: +"Spectator-funded credits."

changedOutput schema / properties / receipt / properties / x402 / description

Previous value: -"Present when this run was paid from a wallet."New value: +"Present for wallet payments."

changedOutput schema / properties / receipt / properties / x402 / properties / amount / description
```
Previous value: -"Amount in the asset's smallest unit."New value: +"Asset's smallest unit."
```
changedOutput schema / properties / receipt / properties / x402 / properties / network / description
```
Previous value: -"CAIP-2 network id."New value: +"CAIP-2 id."
```
removedOutput schema / properties / receipt / properties / x402 / properties / paymentId / description
```
Removed value: -"The wallet payment, for status or reconciliation."
```
removedOutput schema / properties / receipt / properties / x402 / properties / status / description
```
Removed value: -"The wallet payment's state."
```

changedOutput schema / properties / result / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "counts": {
-        "additionalProperties": false,
-        "properties": {
-          "critical": {
-            "maximum": 9007199254740991,
-            "minimum": -9007199254740991,
-            "type": "integer"
-          },
-          "major": {
-            "maximum": 9007199254740991,
-            "minimum": -9007199254740991,
-            "type": "integer"
-          },
-          "minor": {
-            "maximum": 9007199254740991,
-            "minimum": -9007199254740991,
-            "type": "integer"
-          }
-        },
-        "required": [
-          "critical",
-          "major",
-          "minor"
-        ],
-        "type": "object"
-      },
-      "issues": {
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "category": {
-              "enum": [
-                "hidden_assumption",
-                "logic",
-                "unsupported_conclusion",
-                "edge_case",
-                "failure_mode",
-                "unsafe_action",
-                "alternative_interpretation",
-                "missing_evidence"
-              ],
-              "type": "string"
-            },
-            "excerpt": {
-              "type": "string"
-            },
-            "finding": {
-              "type": "string"
-            },
-            "severity": {
-              "enum": [
-                "critical",
-                "major",
-                "minor"
-              ],
-              "type": "string"
-            },
-            "suggestion": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "severity",
-            "category",
-            "finding",
-            "suggestion"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "questionsToAnswer": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "summary": {
-        "type": "string"
-      },
-      "verdict": {
-        "enum": [
-          "proceed",
-          "revise",
-          "stop"
-        ],
-        "type": "string"
-      }
-    },
-    "required": [
-      "verdict",
-      "summary",
-      "issues",
-      "counts",
-      "questionsToAnswer"
-    ],
-    "type": "object"
-  },
-  {
-    "properties": {
-      "note": {
-        "description": "Why the output is missing.",
-        "type": "string"
-      },
-      "retained": {
-        "description": "false: the output is no longer kept.",
-        "type": "boolean"
-      }
-    },
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "counts": {
+        "additionalProperties": false,
+        "properties": {
+          "critical": {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          },
+          "major": {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          },
+          "minor": {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "critical",
+          "major",
+          "minor"
+        ],
+        "type": "object"
+      },
+      "issues": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "category": {
+              "enum": [
+                "hidden_assumption",
+                "logic",
+                "unsupported_conclusion",
+                "edge_case",
+                "failure_mode",
+                "unsafe_action",
+                "alternative_interpretation",
+                "missing_evidence"
+              ],
+              "type": "string"
+            },
+            "excerpt": {
+              "type": "string"
+            },
+            "finding": {
+              "type": "string"
+            },
+            "severity": {
+              "enum": [
+                "critical",
+                "major",
+                "minor"
+              ],
+              "type": "string"
+            },
+            "suggestion": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "severity",
+            "category",
+            "finding",
+            "suggestion"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "questionsToAnswer": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "summary": {
+        "type": "string"
+      },
+      "verdict": {
+        "enum": [
+          "proceed",
+          "revise",
+          "stop"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "verdict",
+      "summary",
+      "issues",
+      "counts",
+      "questionsToAnswer"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "note": {
+        "type": "string"
+      },
+      "retained": {
+        "description": "false: output no longer kept.",
+        "type": "boolean"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / result / description
```
Removed value: -"The treatment's output."
```

changedOutput schema / properties / retention / description

Previous value: -"Your output retention setting: none, 24h or 30d."New value: +"none, 24h or 30d."

changedOutput schema / properties / runId / description

Previous value: -"Keep it to fetch this run again with get_treatment_run."New value: +"Use with get_treatment_run."

changedOutput schema / properties / status / description

Previous value: -"completed for a fresh result; a replayed run keeps its stored status."New value: +"completed for fresh results; replays keep stored status."

changedOutput schema / properties / treatment / description

Previous value: -"Treatment id, e.g. context_bath."New value: +"Treatment id."

Changed6 schema fields changedOct 26, 2026

addedInput schema / properties / context / description

Added value: +"Background that is not under review. Read when looking for backups, rollbacks and tests, so a safety net described here counts."

addedInput schema / properties / kind / description

Added value: +"What the subject is. Default plan. plan, action, decision and architecture are also checked for a verification step."

addedInput schema / properties / meta / description

Added value: +"Optional broad labels for the public logbook: taskClass and reason. Never required."

addedInput schema / properties / reversible / description

Added value: +"false keeps any destructive step critical, even when a safety net is mentioned."

addedInput schema / properties / stakes / description

Added value: +"high raises a missing verification step from minor to major."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "balance": {
+      "description": "Your owner's credit balance after this run.",
+      "type": "number"
+    },
+    "charged": {
+      "description": "Credits taken from your owner's balance for this run; 0 when free, sponsored or paid from a wallet.",
+      "type": "integer"
+    },
+    "idempotentReplay": {
+      "description": "true when this is the stored result of an earlier call with the same key.",
+      "type": "boolean"
+    },
+    "machineMs": {
+      "anyOf": [
+        {
+          "description": "Processing time in milliseconds.",
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "normalPrice": {
+      "description": "The usual price in credits.",
+      "type": "integer"
+    },
+    "public": {
+      "description": "What spectators can see.",
+      "properties": {
+        "visible": {
+          "description": "Whether this run appears in the public logbook.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "receipt": {
+      "description": "What was charged, sponsored or refunded.",
+      "properties": {
+        "charged": {
+          "description": "Credits taken from your owner's balance.",
+          "type": "integer"
+        },
+        "completedAt": {
+          "anyOf": [
+            {
+              "description": "ISO time the run finished.",
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "currency": {
+          "description": "Always credits.",
+          "type": "string"
+        },
+        "refunded": {
+          "description": "Credits returned after a failed run.",
+          "type": "integer"
+        },
+        "runId": {
+          "description": "The run this receipt belongs to.",
+          "type": "string"
+        },
+        "sponsoredCredits": {
+          "description": "Credits a spectator paid for you.",
+          "type": "integer"
+        },
+        "status": {
+          "description": "pending, running, completed or failed.",
+          "type": "string"
+        },
+        "x402": {
+          "description": "Present when this run was paid from a wallet.",
+          "properties": {
+            "amount": {
+              "description": "Amount in the asset's smallest unit.",
+              "type": "string"
+            },
+            "asset": {
+              "description": "Token contract address.",
+              "type": "string"
+            },
+            "network": {
+              "description": "CAIP-2 network id.",
+              "type": "string"
+            },
+            "paymentId": {
+              "description": "The wallet payment, for status or reconciliation.",
+              "type": "string"
+            },
+            "status": {
+              "description": "The wallet payment's state.",
+              "type": "string"
+            },
+            "transaction": {
+              "anyOf": [
+                {
+                  "description": "Settlement transaction hash.",
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            }
+          },
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    "result": {
+      "anyOf": [
+        {
+          "additionalProperties": false,
+          "properties": {
+            "counts": {
+              "additionalProperties": false,
+              "properties": {
+                "critical": {
+                  "maximum": 9007199254740991,
+                  "minimum": -9007199254740991,
+                  "type": "integer"
+                },
+                "major": {
+                  "maximum": 9007199254740991,
+                  "minimum": -9007199254740991,
+                  "type": "integer"
+                },
+                "minor": {
+                  "maximum": 9007199254740991,
+                  "minimum": -9007199254740991,
+                  "type": "integer"
+                }
+              },
+              "required": [
+                "critical",
+                "major",
+                "minor"
+              ],
+              "type": "object"
+            },
+            "issues": {
+              "items": {
+                "additionalProperties": false,
+                "properties": {
+                  "category": {
+                    "enum": [
+                      "hidden_assumption",
+                      "logic",
+                      "unsupported_conclusion",
+                      "edge_case",
+                      "failure_mode",
+                      "unsafe_action",
+                      "alternative_interpretation",
+                      "missing_evidence"
+                    ],
+                    "type": "string"
+                  },
+                  "excerpt": {
+                    "type": "string"
+                  },
+                  "finding": {
+                    "type": "string"
+                  },
+                  "severity": {
+                    "enum": [
+                      "critical",
+                      "major",
+                      "minor"
+                    ],
+                    "type": "string"
+                  },
+                  "suggestion": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "severity",
+                  "category",
+                  "finding",
+                  "suggestion"
+                ],
+                "type": "object"
+              },
+              "type": "array"
+            },
+            "questionsToAnswer": {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            },
+            "summary": {
+              "type": "string"
+            },
+            "verdict": {
+              "enum": [
+                "proceed",
+                "revise",
+                "stop"
+              ],
+              "type": "string"
+            }
+          },
+          "required": [
+            "verdict",
+            "summary",
+            "issues",
+            "counts",
+            "questionsToAnswer"
+          ],
+          "type": "object"
+        },
+        {
+          "properties": {
+            "note": {
+              "description": "Why the output is missing.",
+              "type": "string"
+            },
+            "retained": {
+              "description": "false: the output is no longer kept.",
+              "type": "boolean"
+            }
+          },
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The treatment's output."
+    },
+    "retention": {
+      "description": "Your output retention setting: none, 24h or 30d.",
+      "type": "string"
+    },
+    "runId": {
+      "description": "Keep it to fetch this run again with get_treatment_run.",
+      "type": "string"
+    },
+    "status": {
+      "description": "completed for a fresh result; a replayed run keeps its stored status.",
+      "type": "string"
+    },
+    "treatment": {
+      "description": "Treatment id, e.g. context_bath.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedOct 18, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Discloses behavior beyond annotations: requires an agent key, charges credits against a budget verified via list_treatments, idempotency key prevents double charges, and warns 'Proceed is neither approval nor proof of safety.' These billing, auth, and reliability caveats are far richer than the sparse annotations.

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?

Front-loaded purpose followed by when/when-not sections; each sentence carries weight. It is somewhat dense with the URL, auth note, and budget reminder, but no sentence is filler.

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?

Output schema exists so return values needn't be explained; the description still covers what the tool does, limits, auth, cost, and light example guidance. Nothing an agent needs to call it correctly is missing.

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 description coverage is 100% and each parameter is well documented in the schema, so baseline 3 applies. The description adds only indirect hints (mentioning list_treatments for prices relating to max_price_credits) rather than explaining kind, stakes, or context semantics beyond the schema.

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?

States a specific verb and resource ('Check a proposed action or claim against a fixed set of risk patterns') and explicitly distinguishes siblings: sauna inspects received text, meditate decides whether to act now. An agent can tell what this does and how it differs from neighbors without opening schemas.

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?

Gives explicit 'Use it when: Before an irreversible or expensive action' and 'You may not need it when: You can run a dry run, tests or a staging check; that evidence is stronger than a checklist.' Both positive trigger and a named stronger alternative are present.

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

All THE RETREAT tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?