fix: eval cards (#129)

Author: nina-kollman

evaluators/made-by-traceloop.mdx

@@ -67,10 +67,6 @@ Each evaluator comes with a predefined input and output schema. When using an ev
     Measure how well the LLM response follows given instructions to ensure compliance with specified requirements.
   </Card>
 
-  <Card title="Prompt Perplexity" icon="brain">
-    Measure how predictable/familiar a prompt is to a language model.
-  </Card>
-
   <Card title="Measure Perplexity" icon="hashtag">
     Measure text perplexity from logprobs to assess the predictability and coherence of generated text.
   </Card>
@@ -82,6 +78,10 @@ Each evaluator comes with a predefined input and output schema. When using an ev
   <Card title="Conversation Quality" icon="comments">
     Evaluate conversation quality based on tone, clarity, flow, responsiveness, and transparency.
   </Card>
+
+  <Card title="Context Relevance" icon="hashtag">
+    Validate context relevance to ensure retrieved context is pertinent to the query.
+  </Card>
 </CardGroup>
 
 ### Security & Compliance