Fix empty tool descriptions (#17946)

## Summary
- Ensure direct namespaced MCP tool groups are emitted with a non-empty
namespace description even when namespace metadata is missing or blank.
- Add regression coverage for missing MCP namespace descriptions.

## Cause
Latest `main` can serialize a direct namespaced MCP tool group with an
empty top-level `description`. The namespace description path used
`unwrap_or_default()` when `tool_namespaces` did not include metadata
for that namespace, so the outbound Responses API payload could contain
a tool like `{"type":"namespace","description":""}`. The Responses API
rejects that because namespace tool descriptions must be a non-empty
string.

## Fix
- Add a fallback namespace description: `Tools in the <namespace>
namespace.`
- Preserve provided namespace descriptions after trimming, but treat
blank descriptions as missing.

### Issue I am seeing
This is what I am seeing on the local build.
<img width="1593" height="488" alt="Screenshot 2026-04-15 at 10 55 55
AM"
src="https://github.com/user-attachments/assets/bab668ba-bf17-4c71-be4e-b102202fce57"
/>

---------

Co-authored-by: Sayan Sisodiya <sayan@openai.com>

codex-rs/tools/src/tool_discovery_tests.rs

@@ -253,7 +253,7 @@ fn collect_tool_search_output_tools_preserves_search_order_while_grouping_by_nam
             }),
             ToolSearchOutputTool::Namespace(ResponsesApiNamespace {
                 name: "mcp__docs__".to_string(),
-                description: "Tools from the docs MCP server.".to_string(),
+                description: "Tools in the mcp__docs__ namespace.".to_string(),
                 tools: vec![ResponsesApiNamespaceTool::Function(ResponsesApiTool {
                     name: "search".to_string(),
                     description: "Search docs.".to_string(),
@@ -272,7 +272,7 @@ fn collect_tool_search_output_tools_preserves_search_order_while_grouping_by_nam
 }
 
 #[test]
-fn collect_tool_search_output_tools_falls_back_to_connector_name_description() {
+fn collect_tool_search_output_tools_ignores_blank_connector_description() {
     let gmail_batch_read_email = mcp_tool("gmail-batch-read-email", "Read multiple emails.");
 
     let tools = collect_tool_search_output_tools([ToolSearchResultSource {
@@ -281,7 +281,7 @@ fn collect_tool_search_output_tools_falls_back_to_connector_name_description() {
         tool_name: "_batch_read_email",
         tool: &gmail_batch_read_email,
         connector_name: Some("Gmail"),
-        connector_description: None,
+        connector_description: Some("   "),
     }])
     .expect("collect tool search output tools");