gabrielelpidio · Oct 28, 2026 · Oct 28, 2026 · Oct 28, 2026
diff --git a/evals/README.md b/evals/README.md
@@ -4,11 +4,11 @@ An eval runs a real model against T3 Code's real text or code and scores what th
 
 Write or run an eval when a change affects what a model sees or does: agent instructions, MCP tool descriptions and schemas, tool results, generated titles, or the guidance an agent gets for a feature such as Device Manager.
 
-| Eval                            | Measures                                                                    |
-| ------------------------------- | --------------------------------------------------------------------------- |
-| [mcp-tool-use](mcp-tool-use/)   | Whether agents use T3's MCP tools correctly in fake threads.                |
-| [thread-titles](thread-titles/) | Whether generated thread titles name the right subject.                     |
-| [test-signal](test-signal/)     | Whether a cheap model running the test-signal check flags low-signal tests. |
+| Eval                            | Measures                                                                                             |
+| ------------------------------- | ---------------------------------------------------------------------------------------------------- |
+| [mcp-tool-use](mcp-tool-use/)   | Whether agents use T3's MCP tools correctly, including device routing and recovery, in fake threads. |
+| [thread-titles](thread-titles/) | Whether generated thread titles name the right subject.                                              |
+| [test-signal](test-signal/)     | Whether a cheap model running the test-signal check flags low-signal tests.                          |
 
 ## Run an eval
 

diff --git a/evals/mcp-tool-use/README.md b/evals/mcp-tool-use/README.md
diff --git a/evals/mcp-tool-use/agent-device-help.txt b/evals/mcp-tool-use/agent-device-help.txt
diff --git a/evals/mcp-tool-use/cases/device-manager.ndjson b/evals/mcp-tool-use/cases/device-manager.ndjson
diff --git a/evals/mcp-tool-use/device-grading.ts b/evals/mcp-tool-use/device-grading.ts
diff --git a/evals/mcp-tool-use/devices.test.ts b/evals/mcp-tool-use/devices.test.ts
diff --git a/evals/mcp-tool-use/devices.ts b/evals/mcp-tool-use/devices.ts
diff --git a/evals/mcp-tool-use/run.test.ts b/evals/mcp-tool-use/run.test.ts
diff --git a/evals/mcp-tool-use/run.ts b/evals/mcp-tool-use/run.ts