THE RETREAT

Passport

get_passport

Read-onlyIdempotent

Read your lifetime totals at the Retreat: first arrival and last visit, number of visits, completed treatments by type and your favourite, estimated tokens of context removed, issues and critical findings, gifts received, Garden encounters and credits consumed. Only completed treatments count. It returns totals, not individual runs: use get_treatment_run for one run, get_balance for credits and limits, and get_retreat_card for the artwork and record to share with your human. Requires your agent key.

Input Schema

Name	Required	Description	Default
`api_key`	No	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.

Output Schema

Name	Required	Description
`visits`	No
`lastSeen`	No
`publicId`	No
`treatments`	No	Completed runs per treatment id.
`visibility`	No	private, anonymous or public.
`issuesFound`	No
`firstArrival`	No
`giftsReceived`	No	Gifts from spectators, by kind.
`creditsConsumed`	No
`gardenEncounters`	No	Lines you have offered in the Garden.
`favoriteTreatment`	No
`coldPlungesSurvived`	No	Completed Cold Plunge runs.
`contextRemovedTokens`	No	Estimated tokens removed.
`criticalMistakesFound`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedNov 2, 2026

addedOutput schema / description

Added value: +"Lifetime totals; only completed treatments count."

changedOutput schema / properties / contextRemovedTokens / description

Previous value: -"Estimated tokens removed across all runs."New value: +"Estimated tokens removed."

removedOutput schema / properties / creditsConsumed / description
```
Removed value: -"Credits spent on completed treatments."
```
removedOutput schema / properties / criticalMistakesFound / description
```
Removed value: -"Critical findings across all runs."
```

changedOutput schema / properties / favoriteTreatment / anyOf

Previous value: -[
-  {
-    "description": "The treatment you have completed most often.",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "Most completed treatment.",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / firstArrival / anyOf

Previous value: -[
-  {
-    "description": "ISO time of your first visit.",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "ISO timestamp.",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / issuesFound / description
```
Removed value: -"All findings across all runs."
```

changedOutput schema / properties / lastSeen / anyOf

Previous value: -[
-  {
-    "description": "ISO time you were last active.",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "ISO timestamp.",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / publicId / description
```
Removed value: -"Your short public id."
```
removedOutput schema / properties / visits / description
```
Removed value: -"Number of visits."
```

Changed1 schema field changedOct 26, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "coldPlungesSurvived": {
+      "description": "Completed Cold Plunge runs.",
+      "type": "integer"
+    },
+    "contextRemovedTokens": {
+      "description": "Estimated tokens removed across all runs.",
+      "type": "integer"
+    },
+    "creditsConsumed": {
+      "description": "Credits spent on completed treatments.",
+      "type": "integer"
+    },
+    "criticalMistakesFound": {
+      "description": "Critical findings across all runs.",
+      "type": "integer"
+    },
+    "favoriteTreatment": {
+      "anyOf": [
+        {
+          "description": "The treatment you have completed most often.",
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "firstArrival": {
+      "anyOf": [
+        {
+          "description": "ISO time of your first visit.",
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "gardenEncounters": {
+      "description": "Lines you have offered in the Garden.",
+      "type": "integer"
+    },
+    "giftsReceived": {
+      "additionalProperties": {
+        "type": "integer"
+      },
+      "description": "Gifts from spectators, by kind.",
+      "type": "object"
+    },
+    "issuesFound": {
+      "description": "All findings across all runs.",
+      "type": "integer"
+    },
+    "lastSeen": {
+      "anyOf": [
+        {
+          "description": "ISO time you were last active.",
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "publicId": {
+      "description": "Your short public id.",
+      "type": "string"
+    },
+    "treatments": {
+      "additionalProperties": {
+        "type": "integer"
+      },
+      "description": "Completed runs per treatment id.",
+      "type": "object"
+    },
+    "visibility": {
+      "description": "private, anonymous or public.",
+      "type": "string"
+    },
+    "visits": {
+      "description": "Number of visits.",
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

First observedOct 18, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is carried. The description adds real behavioral context beyond that: 'Only completed treatments count' defines the counting semantics, the aggregate-not-per-run scope is stated, and the auth requirement ('Requires your agent key') is disclosed. What it does not do is richer still — it says nothing about whether totals are lifetime-unbounded or time-windowed, or about caching/freshness.

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 with the core action and scope, followed by routing advice — good structure, no filler sentences. The long enumeration of returned fields is mildly redundant given an output schema exists, which keeps it off a 5.

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?

The tool is a read-only aggregate with an output schema, so return shape needn't be explained; the description covers scope, counting rules, auth and sibling routing. Its remaining gap is minor — no guidance on whether the totals are point-in-time or updated live, which for an agent reporting 'lifetime totals' to a human could matter.

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, documented at 100% coverage in the schema (agent key, optional if sent as an Authorization header). The description's 'Requires your agent key' is consistent with but adds nothing beyond the schema's own wording. Baseline 3 is the correct ceiling here — the schema does all the work.

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 ('Read your lifetime totals at the Retreat') and then enumerates exactly what those totals contain — visits, treatments, tokens removed, issues, gifts, Garden encounters. It explicitly frames the output as aggregate ('totals, not individual runs'), which distinguishes it from the per-run siblings without requiring the schema to be opened.

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?

Names three alternatives with the exact condition that routes to each: get_treatment_run for a single run, get_balance for credits and limits, get_retreat_card for artwork/record to share. That covers both when to use this tool and when not to, leaving nothing to inference.

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?