fix: Update tools API to use current format

skills.json

@@ -18,7 +18,7 @@
       "name": "aiconfig-tools",
       "description": "Guide for giving your AI agents capabilities through tools. Helps you identify what your AI needs to do, create tool definitions, and attach them in a way that makes sense for your framework.",
       "path": "skills/ai-configs/aiconfig-tools",
-      "version": "0.2.0",
+      "version": "0.3.0",
       "compatibility": "Requires LaunchDarkly API token with ai-tool permissions."
     },
     {

skills/ai-configs/aiconfig-create/references/api-quickstart.md

@@ -93,13 +93,9 @@ curl -X PATCH \
   -H "Content-Type: application/json" \
   -H "LD-API-Version: beta" \
   -d '{
-    "model": {
-      "parameters": {
-        "tools": [
-          {"key": "search-database", "version": 1}
-        ]
-      }
-    }
+    "tools": [
+      {"key": "search-database", "version": 1}
+    ]
   }'
 ```
 

skills/ai-configs/aiconfig-tools/SKILL.md

@@ -4,7 +4,7 @@ description: Guide for giving your AI agents capabilities through tools. Helps y
 compatibility: Requires LaunchDarkly API token with ai-tool permissions.
 metadata:
   author: launchdarkly
-  version: "0.2.0"
+  version: "0.3.0"
 ---
 
 # AI Config Tools
@@ -45,7 +45,7 @@ What should the AI be able to do?
 Follow [API Quick Start](references/api-quickstart.md):
 
 1. **Create tool** — `POST /projects/{projectKey}/ai-tools` with key, description, schema
-2. **Schema format** — Use OpenAI function calling format (type, function.name, function.parameters)
+2. **Schema format** — Use JSON Schema format (type: object, properties, required)
 3. **Clear descriptions** — The LLM uses the description to decide when to call
 
 ### Step 3: Attach to Variation
@@ -56,7 +56,7 @@ Tools cannot be attached during config creation. PATCH the variation:
 PATCH /projects/{projectKey}/ai-configs/{configKey}/variations/{variationKey}
 ```
 
-Body: `{"model": {"parameters": {"tools": [{"key": "tool-name", "version": 1}]}}}`
+Body: `{"tools": [{"key": "tool-name", "version": 1}]}`
 
 See [API Quick Start](references/api-quickstart.md) for full curl example.
 
@@ -71,7 +71,7 @@ See [API Quick Start](references/api-quickstart.md) for full curl example.
    ```bash
    GET /projects/{projectKey}/ai-configs/{configKey}/variations/{variationKey}
    ```
-   Check `model.parameters.tools` includes your tool key.
+   Check the `tools` array includes your tool key.
 
 3. **Report results:**
    - ✓ Tool created with valid schema
@@ -88,7 +88,7 @@ LangGraph, CrewAI, AutoGen often generate schemas from function definitions. You
 |-----------|--------|
 | Tool already exists (409) | Use existing or create with different key |
 | Wrong endpoint | Use `/ai-tools`, not `/ai-configs/tools` |
-| Schema invalid | Use OpenAI function format |
+| Schema invalid | Use JSON Schema format (type: object, properties, required) |
 
 ## What NOT to Do
 

skills/ai-configs/aiconfig-tools/references/api-quickstart.md

@@ -2,7 +2,7 @@
 
 Create and manage tools using the LaunchDarkly API.
 
-**Endpoint:** `https://app.launchdarkly.com/api/v2/projects/{projectKey}/ai-tools`  
+**Endpoint:** `https://app.launchdarkly.com/api/v2/projects/{projectKey}/ai-tools`
 Do NOT use `/ai-configs/tools` — that endpoint does not exist.
 
 ## Create a Tool
@@ -16,23 +16,24 @@ curl -X POST \
     "key": "search-database",
     "description": "Search the customer database",
     "schema": {
-      "type": "function",
-      "function": {
-        "name": "search_database",
-        "description": "Search for records",
-        "parameters": {
-          "type": "object",
-          "properties": {
-            "query": {"type": "string", "description": "Search query"},
-            "limit": {"type": "integer", "default": 10}
-          },
-          "required": ["query"]
-        }
-      }
+      "type": "object",
+      "properties": {
+        "query": {"type": "string", "description": "Search query"},
+        "limit": {"type": "integer", "description": "Max results to return"}
+      },
+      "required": ["query"]
     }
   }'
 ```
 
+### Optional Fields
+
+| Field | Description |
+|-------|-------------|
+| `maintainerId` | User ID of the tool maintainer |
+| `maintainerTeamKey` | Team key for tool ownership |
+| `customParameters` | Additional custom parameters as JSON object |
+
 ## Attach to Variation
 
 ```bash
@@ -42,13 +43,9 @@ curl -X PATCH \
   -H "Content-Type: application/json" \
   -H "LD-API-Version: beta" \
   -d '{
-    "model": {
-      "parameters": {
-        "tools": [
-          {"key": "search-database", "version": 1}
-        ]
-      }
-    }
+    "tools": [
+      {"key": "search-database", "version": 1}
+    ]
   }'
 ```
 
@@ -70,19 +67,17 @@ curl -X GET \
 
 ## Schema Format
 
-Use OpenAI function calling format:
+Use JSON Schema format:
 
 ```json
 {
-  "type": "function",
-  "function": {
-    "name": "function_name",
-    "description": "What the LLM uses to decide when to call",
-    "parameters": {
-      "type": "object",
-      "properties": { ... },
-      "required": [ ... ]
-    }
-  }
+  "type": "object",
+  "properties": {
+    "query": {"type": "string", "description": "Search query"},
+    "limit": {"type": "integer", "description": "Max results"}
+  },
+  "required": ["query"]
 }
 ```
+
+The tool `key` and `description` are set at the top level, not inside the schema.