Tighten the opening paragraph

README.md

@@ -39,14 +39,14 @@ model-index:
 
 # CodeIntel-150M
 
-CodeIntel-150M is a 149M-parameter embedding model for **finding the code a bug report is about**. Give it an issue
-written by a user and it retrieves the functions and classes in a Python or TypeScript repository that a fix will
-touch. When the issue only describes a symptom and names no code, it does this **about 55% better than any other open
-model its size**. It is also ahead when the issue does name code (+27%) and at matching tests to the code they cover
-(+23%).
-
-It also handles call site -> definition navigation and code search (it leads its size class on CoIR StackOverflow QA
-and CodeSearchNet Python). It is a fine-tune of
+CodeIntel-150M is a 149M-parameter embedding model for **issue-to-code localization**: given a bug report or feature
+request, it retrieves the functions and classes in a Python or TypeScript repository that a fix is likely to
+modify. On issues that describe only symptoms, with no reference to the relevant code, it outperforms every other
+open embedding model of comparable size by **roughly 55%**. It also leads on issues that reference code directly
+(+27%) and on test-to-implementation retrieval (+23%).
+
+Beyond localization, it supports call-site-to-definition navigation and code search, where it leads its size class on CoIR StackOverflow QA
+and CodeSearchNet Python. It is a fine-tune of
 [granite-embedding-english-r2](https://huggingface.co/ibm-granite/granite-embedding-english-r2) (ModernBERT,
 Apache-2.0). It runs locally, including as a 325 MB INT8 ONNX model, and needs no remote code.