Adds optional _meta field to Tool (#339)

<!-- Provide a brief summary of your changes -->

## Motivation and Context
The recently released openAI [Apps SDK
](https://developers.openai.com/apps-sdk/reference/#_meta-fields-the-client-provides)adds
a '__meta_' field on the Tool Descriptor. This would be in addition to
it being available on Messages. It remains optional and defaults to an
empty json object, following existing conventions.


## How Has This Been Tested?
Unit tests for serialization added

## Breaking Changes
N/A

## Types of changes
<!-- What types of changes does your code introduce? Put an `x` in all
the boxes that apply: -->
- [ ] Bug fix (non-breaking change which fixes an issue)
- [X] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update

## Checklist
<!-- Go over all the following points, and put an `x` in all the boxes
that apply. -->
- [X] I have read the [MCP
Documentation](https://modelcontextprotocol.io)
- [X] My code follows the repository's style guidelines
- [X] New and existing tests pass locally
- [X] I have added appropriate error handling
- [X] I have added or updated documentation as needed

## Additional context
https://developers.openai.com/apps-sdk

https://developers.openai.com/apps-sdk/reference/#_meta-fields-the-client-provides

---------

Co-authored-by: Pavel Gorgulov <devcrocod@gmail.com>

kotlin-sdk-server/src/commonMain/kotlin/io/modelcontextprotocol/kotlin/sdk/server/Server.kt

@@ -3,6 +3,7 @@ package io.modelcontextprotocol.kotlin.sdk.server
 import io.github.oshai.kotlinlogging.KotlinLogging
 import io.modelcontextprotocol.kotlin.sdk.CallToolRequest
 import io.modelcontextprotocol.kotlin.sdk.CallToolResult
+import io.modelcontextprotocol.kotlin.sdk.EmptyJsonObject
 import io.modelcontextprotocol.kotlin.sdk.GetPromptRequest
 import io.modelcontextprotocol.kotlin.sdk.GetPromptResult
 import io.modelcontextprotocol.kotlin.sdk.Implementation
@@ -30,6 +31,7 @@ import kotlinx.atomicfu.atomic
 import kotlinx.atomicfu.update
 import kotlinx.collections.immutable.persistentListOf
 import kotlinx.coroutines.CancellationException
+import kotlinx.serialization.json.JsonObject
 
 private val logger = KotlinLogging.logger {}
 
@@ -243,6 +245,7 @@ public open class Server(
      * @param inputSchema The expected input schema for the tool.
      * @param outputSchema The optional expected output schema for the tool.
      * @param toolAnnotations Optional additional tool information.
+     * @param _meta Optional metadata as a [JsonObject].
      * @param handler A suspend function that handles executing the tool when called by the client.
      * @throws IllegalStateException If the server does not support tools.
      */
@@ -254,9 +257,18 @@ public open class Server(
         title: String? = null,
         outputSchema: Tool.Output? = null,
         toolAnnotations: ToolAnnotations? = null,
+        @Suppress("LocalVariableName") _meta: JsonObject? = null,
         handler: suspend (CallToolRequest) -> CallToolResult,
     ) {
-        val tool = Tool(name, title, description, inputSchema, outputSchema, toolAnnotations)
+        val tool = Tool(
+            name = name,
+            title = title,
+            description = description,
+            inputSchema = inputSchema,
+            outputSchema = outputSchema,
+            annotations = toolAnnotations,
+            _meta = _meta ?: EmptyJsonObject,
+        )
         addTool(tool, handler)
     }