Simplify MCP tool handler plumbing (#21595)

## Why
The MCP tool path had accumulated a few core-owned special cases: a
dedicated payload variant, resolver plumbing, a legacy `AfterToolUse`
translation path, and a side channel for parallel-call metadata. That
made `ToolRegistry` and the spec builder know more about MCP than they
needed to.

This change moves MCP-specific execution details back onto `ToolInfo`
and `McpHandler` so `codex-core` can treat MCP calls like normal
function calls while still preserving MCP-specific dispatch and
telemetry behavior where it belongs.

## What changed
- removed `resolve_mcp_tool_info`, `ToolPayload::Mcp`, `ToolKind`, and
the remaining registry-side MCP resolver path
- stored MCP routing metadata directly on `McpHandler` and `ToolInfo`,
including `supports_parallel_tool_calls`
- deleted the legacy `AfterToolUse` consumer in `core`, which removes
the need for handler-specific `after_tool_use_payload` implementations
- switched tool-result telemetry to handler-provided tags and kept
MCP-specific dispatch payload construction inside the handler
- simplified tool spec planning/building by passing `ToolInfo` directly
and dropping the direct/deferred MCP wrapper structs and the
parallel-server side table

## Testing
- `cargo check -p codex-core -p codex-mcp -p codex-otel`
- `cargo test -p codex-core
mcp_parallel_support_uses_exact_payload_server`
- `cargo test -p codex-core
direct_mcp_tools_register_namespaced_handlers`
- `cargo test -p codex-core
search_tool_description_lists_each_mcp_source_once`
- `cargo test -p codex-mcp
list_all_tools_uses_startup_snapshot_while_client_is_pending`
- `just fix -p codex-core -p codex-mcp -p codex-otel`

codex-rs/core/src/tools/context_tests.rs

@@ -61,10 +61,8 @@ fn mcp_code_mode_result_serializes_full_call_tool_result() {
         })),
     };
 
-    let result = output.code_mode_result(&ToolPayload::Mcp {
-        server: "server".to_string(),
-        tool: "tool".to_string(),
-        raw_arguments: "{}".to_string(),
+    let result = output.code_mode_result(&ToolPayload::Function {
+        arguments: "{}".to_string(),
     });
 
     assert_eq!(
@@ -106,10 +104,8 @@ fn mcp_tool_output_response_item_includes_wall_time() {
 
     let response = output.to_response_item(
         "mcp-call-1",
-        &ToolPayload::Mcp {
-            server: "server".to_string(),
-            tool: "tool".to_string(),
-            raw_arguments: "{}".to_string(),
+        &ToolPayload::Function {
+            arguments: "{}".to_string(),
         },
     );
 
@@ -160,10 +156,8 @@ fn mcp_tool_output_response_item_truncates_large_structured_content() {
 
     let response = output.to_response_item(
         "mcp-call-large",
-        &ToolPayload::Mcp {
-            server: "server".to_string(),
-            tool: "tool".to_string(),
-            raw_arguments: "{}".to_string(),
+        &ToolPayload::Function {
+            arguments: "{}".to_string(),
         },
     );
 
@@ -205,10 +199,8 @@ fn mcp_tool_output_response_item_preserves_content_items() {
 
     let response = output.to_response_item(
         "mcp-call-2",
-        &ToolPayload::Mcp {
-            server: "server".to_string(),
-            tool: "tool".to_string(),
-            raw_arguments: "{}".to_string(),
+        &ToolPayload::Function {
+            arguments: "{}".to_string(),
         },
     );
 
@@ -259,10 +251,8 @@ fn mcp_tool_output_code_mode_result_stays_raw_call_tool_result() {
         truncation_policy: TruncationPolicy::Bytes(64),
     };
 
-    let result = output.code_mode_result(&ToolPayload::Mcp {
-        server: "server".to_string(),
-        tool: "tool".to_string(),
-        raw_arguments: "{}".to_string(),
+    let result = output.code_mode_result(&ToolPayload::Function {
+        arguments: "{}".to_string(),
     });
 
     assert_eq!(