Punctuation and grammar fixes

Author: agu-z

docs/protocol/initialization.mdx

@@ -65,9 +65,9 @@ See [Capabilities](#capabilities) to learn how non-breaking features are introdu
 
 The `initialize` request **MUST** include the latest protocol version the Client supports.
 
-If the Agent supports the requested version, it **MUST** respond with the same version. Otherwise, the server **MUST** respond with latest version it supports.
+If the Agent supports the requested version, it **MUST** respond with the same version. Otherwise, the server **MUST** respond with the latest version it supports.
 
-If the Client does not support the version specified by the Agent in the `initialize` response, the Client **SHOULD** close the connection and inform the User about it.
+If the Client does not support the version specified by the Agent in the `initialize` response, the Client **SHOULD** close the connection and inform the user about it.
 
 
 ## Capabilities
@@ -89,7 +89,7 @@ The Client **SHOULD** specify whether it supports the following capability:
 
 #### FileSystem
 
-The Client **MAY** expose its FileSystem abstraction to varying degree:
+The Client **MAY** expose its FileSystem abstraction to varying degrees:
 
 - `readTextFile`: The `fs/read_text_file` method is available.
 - `writeTextFile`: The `fs/write_text_file` method is available.

docs/protocol/prompt-turn.mdx

@@ -40,7 +40,7 @@ The turn begins when the Client sends a `session/prompt` request containing the
 }
 ```
 
-This message **MAY** include various types of [content](./content) including text, images, audio, references to external resources, and embedded context.
+This message **MAY** include various types of [content](./content), including text, images, audio, references to external resources, and embedded context.
 
 {/* todo! move prompt capabilities to this page */}
 Clients **MUST** only include types of content supported by the Agent according to its [Prompt Capabilities](./initialization#prompt-capabilities).
@@ -70,7 +70,7 @@ The Agent reports the model's output to the Client via `session/update` notifica
 }
 ```
 
-If the model requested tool calls, these are also reported as soon:
+If the model requested tool calls, these are also reported immediately:
 
 ```json
 {
@@ -111,7 +111,7 @@ If tool calls were requested, the Agent processes each [tool](./tool-call).
 
 Before proceeding with execution, the Agent **MAY** request permission from the Client via the `session/request_permission` method.
 
-Once permission is granted (if required), the Agent **SHOULD** invoke the tool and report a status update marking the tool as `in_progress`
+Once permission is granted (if required), the Agent **SHOULD** invoke the tool and report a status update marking the tool as `in_progress`:
 
 ```json
 {
@@ -166,7 +166,7 @@ The Agent sends the tool results back to the language model as another request.
 
 The cycle returns to [step 2](#2-agent-processing), continuing until the language model completes its response without requesting additional tool calls or the turn gets stopped by the Agent or cancelled by the Client.
 
-## Stop reasons
+## Stop Reasons
 
 When an Agent stops a turn, it must specify the corresponding `StopReason`:
 

docs/protocol/session-setup.mdx

@@ -162,7 +162,7 @@ The `cwd` (current working directory) parameter establishes the file system cont
 
 - **SHOULD** be an absolute path
 - **SHOULD** serve as a boundary for tool operations on the file system
-- **MUST** be used for the session regardless of where the Agent subprocess was spawned in
+- **MUST** be used for the session regardless of where the Agent subprocess was spawned
 
 ## MCP Servers