diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts
index 22cdf793eeb..59fcbf6644f 100644
--- a/ui/litellm-dashboard/src/lib/http/schema.d.ts
+++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts
@@ -7980,11 +7980,12 @@ export interface paths {
          * Test Model
          * @description Run the live checks on a model, the way a client would use it, and report what works.
          *
-         *     Each selected endpoint gets one two-turn conversation with a long system prompt and a tool. Turn 1 asks
-         *     a question the tool answers, turn 2 sends the tool result back. Three checks come out of it:
+         *     Each selected endpoint gets one three-turn conversation with a long system prompt and a tool. Turn 1 asks
+         *     a question the tool answers, turn 2 sends the tool result back, turn 3 asks a follow-up that needs the
+         *     answer from turn 2. Three checks come out of it:
          *
-         *     - `conversation`: both turns parse, turn 1 calls the tool, turn 2 uses the tool result
-         *     - `prompt_caching`: turn 2 reports cached input tokens, with no cache markers in the request
+         *     - `conversation`: every turn parses, turn 1 calls the tool, turn 2 uses the tool result, turn 3 carries it on
+         *     - `prompt_caching`: turns 2 and 3 report cached input tokens, with no cache markers in the request
          *     - `cost_tracking`: every turn carries a non-zero response cost, and the spend log row lands when a
          *       database is connected
          *