Update XML doc comments for sampling specification changes

- Update Temperature property with detailed description of randomness control and client MAY modify/ignore
- Fix MaxTokens property to indicate client MUST respect this parameter (removed contradictory remark)
- Add remark to StopSequences noting client MAY modify or ignore
- Add remark to Metadata noting client MAY modify or ignore
- Add remark to Messages about not retaining messages between requests
- Update CreateMessageResult.StopReason endTurn description to match spec wording

Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com>

Author: Copilot

src/ModelContextProtocol.Core/Protocol/CreateMessageRequestParams.cs

@@ -33,25 +33,38 @@ public sealed class CreateMessageRequestParams : RequestParams
     /// Gets or sets the maximum number of tokens to generate in the LLM response, as requested by the server.
     /// </summary>
     /// <remarks>
+    /// <para>
     /// A token is generally a word or part of a word in the text. Setting this value helps control
-    /// response length and computation time. The client can choose to sample fewer tokens than requested.
+    /// response length and computation time.
+    /// </para>
+    /// <para>
+    /// The client MUST respect the <see cref="MaxTokens"/> parameter.
+    /// </para>
     /// </remarks>
     [JsonPropertyName("maxTokens")]
     public required int MaxTokens { get; set; }
 
     /// <summary>
     /// Gets or sets the messages requested by the server to be included in the prompt.
     /// </summary>
+    /// <remarks>
+    /// The list of messages in a sampling request SHOULD NOT be retained between separate requests.
+    /// </remarks>
     [JsonPropertyName("messages")]
     public IList<SamplingMessage> Messages { get; set; } = [];
 
     /// <summary>
     /// Gets or sets optional metadata to pass through to the LLM provider.
     /// </summary>
     /// <remarks>
+    /// <para>
     /// The format of this metadata is provider-specific and can include model-specific settings or
     /// configuration that isn't covered by standard parameters. This allows for passing custom parameters
     /// that are specific to certain AI models or providers.
+    /// </para>
+    /// <para>
+    /// The client MAY modify or ignore metadata.
+    /// </para>
     /// </remarks>
     [JsonPropertyName("metadata")]
     public JsonElement? Metadata { get; set; }
@@ -90,6 +103,9 @@ public sealed class CreateMessageRequestParams : RequestParams
     /// sequence exactly matches one of the provided sequences. Common uses include ending markers like "END", punctuation
     /// like ".", or special delimiter sequences like "###".
     /// </para>
+    /// <para>
+    /// The client MAY modify or ignore stop sequences.
+    /// </para>
     /// </remarks>
     [JsonPropertyName("stopSequences")]
     public IList<string>? StopSequences { get; set; }
@@ -106,6 +122,15 @@ public sealed class CreateMessageRequestParams : RequestParams
     /// <summary>
     /// Gets or sets the temperature to use for sampling, as requested by the server.
     /// </summary>
+    /// <remarks>
+    /// <para>
+    /// Temperature controls randomness in model responses. Higher values produce higher randomness,
+    /// and lower values produce more stable output. The valid range depends on the model provider.
+    /// </para>
+    /// <para>
+    /// The client MAY modify or ignore this value.
+    /// </para>
+    /// </remarks>
     [JsonPropertyName("temperature")]
     public float? Temperature { get; set; }
 

src/ModelContextProtocol.Core/Protocol/CreateMessageResult.cs

@@ -41,7 +41,7 @@ public sealed class CreateMessageResult : Result
     /// <remarks>
     /// Standard values include:
     /// <list type="bullet">
-    ///   <item><term>endTurn</term><description>The model naturally completed its response.</description></item>
+    ///   <item><term>endTurn</term><description>The participant is yielding the conversation to the other party.</description></item>
     ///   <item><term>maxTokens</term><description>The response was truncated due to reaching token limits.</description></item>
     ///   <item><term>stopSequence</term><description>A specific stop sequence was encountered during generation.</description></item>
     ///   <item><term>toolUse</term><description>The model wants to use one or more tools.</description></item>