TuneWorks

Create session

create_session

Saves a new TuneWorks driving session. Deletes are not supported.

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": {
      "vehicleId": "<vehicleId>",
      "sessionDate": "<sessionDate>",
      "sessionFormat": "<sessionFormat>"
    },
    "name": "create_session"
  }
}

Input Schema

Name	Required	Description
`track`	No
`worked`	No
`braking`	No
`drivers`	No
`setupId`	No
`bestTime`	No
`location`	No
`traction`	No
`eventName`	No
`eventType`	No
`midCorner`	No
`vehicleId`	Yes
`cornerExit`	No
`dataLogIds`	No
`didNotWork`	No
`cornerEntry`	No
`sessionDate`	Yes	Session date in YYYY-MM-DD format. Natural date strings are accepted but YYYY-MM-DD is preferred.
`sessionFormat`	Yes
`overallBalance`	No
`performanceFigures`	No
`suggestedSetupChange`	No
`additionalSessionDetails`	No

Output Schema

Name	Required	Description
`url`	No
`list`	No
`tool`	Yes	TuneWorks MCP tool name that produced this result.
`user`	No
`setup`	No
`status`	Yes	Stable result status such as ok, created, updated, sent, auth_required, or confirmation_required.
`message`	No
`outcome`	No	Optional domain outcome for an otherwise successful read.
`session`	No
`tracker`	No
`vehicle`	No
`activation`	No
`modification`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 24, 2026

changedOutput schema / description

Previous value: -"TuneWorks app object create/update result with the saved object and connected user."New value: +"TuneWorks app object create/update result with the saved object, connected user, and next activation actions."

addedOutput schema / properties / activation

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "goal": {
+      "const": "optimize_vehicle",
+      "type": "string"
+    },
+    "missingData": {
+      "items": {
+        "enum": [
+          "vehicle",
+          "accessible_vehicle_id",
+          "baseline_setup",
+          "driving_session",
+          "vehicle_build_state",
+          "vehicle_logs",
+          "structured_vehicle_modifications"
+        ],
+        "type": "string"
+      },
+      "type": "array",
+      "uniqueItems": true
+    },
+    "nextActions": {
+      "items": {
+        "oneOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "arguments": {
+                "additionalProperties": false,
+                "properties": {
+                  "vehicleId": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "vehicleId"
+                ],
+                "type": "object"
+              },
+              "optional": {
+                "type": "boolean"
+              },
+              "reason": {
+                "type": "string"
+              },
+              "requiredInputs": {
+                "items": {
+                  "enum": [
+                    "year",
+                    "make",
+                    "model",
+                    "purpose",
+                    "displacement",
+                    "engineType",
+                    "aspiration",
+                    "cylindersOrRotors",
+                    "fuel",
+                    "fuelRating",
+                    "setupName",
+                    "setupDate",
+                    "sessionDate",
+                    "sessionFormat",
+                    "modifications",
+                    "category",
+                    "system",
+                    "status",
+                    "brand",
+                    "partName"
+                  ],
+                  "type": "string"
+                },
+                "type": "array",
+                "uniqueItems": true
+              },
+              "tool": {
+                "enum": [
+                  "create_vehicle",
+                  "list_vehicles",
+                  "get_vehicle_context",
+                  "create_setup",
+                  "create_session",
+                  "update_vehicle",
+                  "create_vehicle_modification"
+                ],
+                "type": "string"
+              },
+              "type": {
+                "const": "tool",
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "tool",
+              "reason"
+            ],
+            "type": "object"
+          },
+          {
+            "additionalProperties": false,
+            "properties": {
+              "action": {
+                "enum": [
+                  "select_vehicle",
+                  "optimize_vehicle"
+                ],
+                "type": "string"
+              },
+              "optional": {
+                "type": "boolean"
+              },
+              "reason": {
+                "type": "string"
+              },
+              "type": {
+                "const": "assistant",
+                "type": "string"
+              }
+            },
+            "required": [
+              "type",
+              "action",
+              "reason"
+            ],
+            "type": "object"
+          }
+        ]
+      },
+      "type": "array"
+    },
+    "recommendedData": {
+      "items": {
+        "enum": [
+          "vehicle",
+          "accessible_vehicle_id",
+          "baseline_setup",
+          "driving_session",
+          "vehicle_build_state",
+          "vehicle_logs",
+          "structured_vehicle_modifications"
+        ],
+        "type": "string"
+      },
+      "type": "array",
+      "uniqueItems": true
+    },
+    "requestedVehicleId": {
+      "type": "string"
+    },
+    "stage": {
+      "enum": [
+        "empty_garage",
+        "select_vehicle",
+        "vehicle_selected",
+        "vehicle_created",
+        "collecting_baseline_data",
+        "ready_to_optimize"
+      ],
+      "type": "string"
+    },
+    "vehicleId": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "goal",
+    "stage",
+    "missingData",
+    "recommendedData",
+    "nextActions"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / message
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / modification
```
Added value: +{
+  "type": "object"
+}
```

addedOutput schema / properties / outcome

Added value: +{
+  "description": "Optional domain outcome for an otherwise successful read.",
+  "enum": [
+    "no_vehicles",
+    "vehicle_not_found",
+    "vehicle_selection_required",
+    "no_data"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / status / description

Previous value: -"Result status such as ok, created, updated, sent, auth_required, or confirmation_required."New value: +"Stable result status such as ok, created, updated, sent, auth_required, or confirmation_required."

First observedOct 18, 2026

TDQS

C2.4/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write-and-safe profile is covered. The description adds nothing about required fields, validation of vehicleId, whether dataLogIds must reference existing logs, or what the response returns — and 'Deletes are not supported' is irrelevant boilerplate for a create tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Very short and front-loaded, so it doesn't waste the reader's time. But the second sentence earns no place — it restates an obvious limitation of a create endpoint rather than adding guidance or parameter meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be explained. However, a 22-param create tool with only 3 required fields and near-zero schema coverage needs the description to orient the agent toward required inputs and field purposes; it does none of that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

22 parameters at 5% schema description coverage, and the description contributes zero parameter semantics. It doesn't mention that vehicleId, sessionDate, and sessionFormat are required, nor explain the many free-text session fields (worked, braking, cornerEntry, overallBalance) or the two enums.

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 ('Saves a new TuneWorks driving session'), which is precise enough to distinguish it from update_session, copy_session, and archive_session siblings. The trailing 'Deletes are not supported' sentence muddies rather than clarifies scope.

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

Usage Guidelines2/5

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

No indication of when to call this versus update_session (for editing an existing session) or copy_session (for duplicating one). The only contextual statement given — that deletes aren't supported — is a negative that doesn't route the agent anywhere useful.

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

All TuneWorks 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?