Mention response parser parameter in doc (#3496)

Author: michalkulakowski

docs/parameters.md

@@ -120,6 +120,7 @@ Task specific parameters for different tasks (text generation/image generation/e
 | `--dynamic_split_fuse`        | `bool`       | Enables dynamic split fuse algorithm. Default: true.                                                           |
 | `--max_prompt_len`            | `integer`    | Sets NPU specific property for maximum number of tokens in the prompt.                                         |
 | `--kv_cache_precision`        | `string`     | Reduced kv cache precision to `u8` lowers the cache size consumption. Accepted values: `u8` or empty (default).|
+| `--response_parser`           | `string`     | Type of parser to use for tool calls and reasoning in model output. Currently supported: [qwen3, llama3, hermes3, phi4] |
 
 ### Image generation
 | option                            | Value format | Description                                                                                                         |

src/llm/response_parsers/response_parser.hpp

@@ -33,7 +33,6 @@ class ResponseParser {
 public:
     ResponseParser() = delete;
     explicit ResponseParser(ov::genai::Tokenizer& tokenizer, std::string parserName) {
-        // Parser name is read from tokenizer_config.json, "response_parser_name" field.
         if (parserName == "llama3") {
             parser_impl = std::make_unique<Llama3ResponseParser>(tokenizer);
         } else if (parserName == "qwen3") {