diff --git a/council/controllers/llm_controller.py b/council/controllers/llm_controller.py
index ff2c70cd..c0137852 100644
--- a/council/controllers/llm_controller.py
+++ b/council/controllers/llm_controller.py
@@ -45,7 +45,7 @@ def __str__(self):
     @llm_class_validator
     def validate(self):
         if self._score < 0 or self._score > 10:
-            raise LLMParsingException(f"Score {self._score} is invalid, value must be between 0 and 10.")
+            raise LLMParsingException(f"Specialist's score `{self._score}` is invalid, value must be between 0 and 10.")
 
 
 class LLMController(ControllerBase):
diff --git a/council/evaluators/llm_evaluator.py b/council/evaluators/llm_evaluator.py
index 856509e9..c9986070 100644
--- a/council/evaluators/llm_evaluator.py
+++ b/council/evaluators/llm_evaluator.py
@@ -9,7 +9,7 @@
 from council.contexts import AgentContext, ChatMessage, ScoredChatMessage, ContextBase
 from council.evaluators import EvaluatorBase, EvaluatorException
 from council.llm import LLMBase, MonitoredLLM, llm_property, LLMAnswer, LLMMessage
-from council.llm.llm_answer import LLMParsingException
+from council.llm.llm_answer import LLMParsingException, llm_class_validator
 from council.utils import Option
 
 
@@ -37,6 +37,11 @@ def justification(self) -> str:
     def __str__(self):
         return f"Message `{self._index}` graded `{self._grade}` with the justification: `{self._justification}`"
 
+    @llm_class_validator
+    def validate(self):
+        if self._grade < 0.0 or self._grade > 10.0:
+            raise LLMParsingException(f"Grade `{self._grade}` is invalid, value must be between 0.0 and 10.0")
+
 
 class LLMEvaluator(EvaluatorBase):
     """Evaluator using an `LLM` to evaluate chain responses."""
diff --git a/council/llm/llm_answer.py b/council/llm/llm_answer.py
index 90075e6b..160d28bd 100644
--- a/council/llm/llm_answer.py
+++ b/council/llm/llm_answer.py
@@ -39,7 +39,7 @@ def rank(self) -> int:
         return self._rank
 
     def __str__(self):
-        return f"{self._name} {{{self._description}, expected response type `{self._type}`}}"
+        return f"{self._name}: {{{self._description}, expected response type `{self._type.__name__}`}}"
 
     def can_parse(self, value: Any) -> bool:
         try:
diff --git a/council/scorers/llm_similarity_scorer.py b/council/scorers/llm_similarity_scorer.py
index 72ae457b..257c5cfc 100644
--- a/council/scorers/llm_similarity_scorer.py
+++ b/council/scorers/llm_similarity_scorer.py
@@ -4,7 +4,7 @@
 from .scorer_base import ScorerBase
 from council.contexts import ChatMessage, ScorerContext, ContextBase
 from council.llm import LLMBase, LLMMessage, MonitoredLLM, llm_property, LLMAnswer
-from ..llm.llm_answer import LLMParsingException
+from ..llm.llm_answer import LLMParsingException, llm_class_validator
 from ..utils import Option
 
 
@@ -26,6 +26,11 @@ def justification(self) -> str:
     def __str__(self):
         return f"Similarity score is {self.score} with the justification: {self._justification}"
 
+    @llm_class_validator
+    def validate(self):
+        if self._score < 0 or self._score > 100:
+            raise LLMParsingException(f"Similarity Score `{self._score}` is invalid, value must be between 0 and 100.")
+
 
 class LLMSimilarityScorer(ScorerBase):
     """
@@ -100,7 +105,7 @@ def _build_system_message(self) -> LLMMessage:
             "1. Compare the {expected} message and the {actual} message.",
             "2. Score 0 (2 messages are unrelated) to 100 (the 2 messages have the same content).",
             "3. Your score must be fair.",
-            "\n#FORMATTING",
+            "\n# FORMATTING",
             self._llm_answer.to_prompt(),
         ]
         return LLMMessage.system_message("\n".join(system_prompt))
diff --git a/docs/source/getting_started/first_example.ipynb b/docs/source/getting_started/first_example.ipynb
index 67e899b4..9da16e57 100644
--- a/docs/source/getting_started/first_example.ipynb
+++ b/docs/source/getting_started/first_example.ipynb
@@ -49,7 +49,7 @@
     "import os\n",
     "\n",
     "dotenv.load_dotenv()\n",
-    "print(os.getenv(\"OPENAI_API_KEY\", None) is not None )\n",
+    "print(os.getenv(\"OPENAI_API_KEY\", None) is not None)\n",
     "\n",
     "openai_llm = OpenAILLM.from_env()\n"
    ],
@@ -73,7 +73,7 @@
    "source": [
     "prompt = \"You are responding to every prompt with a short poem titled hello world\"\n",
     "hw_skill = LLMSkill(llm=openai_llm, system_prompt=prompt)\n",
-    "hw_chain = Chain(name=\"Hello World\", description=\"Answers with a poem about titled Hello World\", runners=[hw_skill])\n"
+    "hw_chain = Chain(name=\"Hello World\", description=\"Answers with a poem titled Hello World\", runners=[hw_skill])\n"
    ],
    "metadata": {
     "collapsed": false