[DOC] Update VectorDBTool: document runtime override for index and embedding_field (#12203)

* Update VectorDBTool docs: index and embedding_field are now optional

index and embedding_field can now be provided at runtime by the LLM
(e.g., via function calling in conversational agents). Runtime values
take priority over registered defaults.

Resolves #12202

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>

* Keep index and embedding_field as Required, add runtime override note

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>

* Apply suggestions from code review

Co-authored-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

---------

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Co-authored-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

Author: ohltyler

_ml-commons-plugin/agents-tools/tools/vector-db-tool.md

@@ -219,8 +219,8 @@ The following table lists all tool parameters that are available when registerin
 Parameter	| Type | Required/Optional | Description	
 :--- | :--- | :--- | :---
 `model_id` | String | Required | The model ID of the model to use at search time.
-`index` | String | Required | The index to search.
-`embedding_field` | String | Required | When the model encodes raw text documents, the encoding result is saved in a field. Specify this field as the `embedding_field`. Neural search matches documents to the query by calculating the similarity score between the query text and the text in the document's `embedding_field`.
+`index` | String | Required | The index to search. This value can also be provided at runtime by the LLM; runtime values take precedence over registered defaults.
+`embedding_field` | String | Required | When the model encodes raw text documents, the encoding result is saved in a field. Specify this field as the `embedding_field`. Neural search matches documents to the query by calculating the similarity score between the query text and the text in the document's `embedding_field`. This value can also be provided at runtime by the LLM; runtime values take precedence over registered defaults.
 `source_field` | String | Required | The document field or fields to return. You can provide a list of multiple fields as an array of strings, for example, `["field1", "field2"]`.
 `input` | String | Required for flow agent | Runtime input sourced from flow agent parameters. If using a large language model (LLM), this field is populated with the LLM response.
 `doc_size` | Integer | Optional | The number of documents to fetch. Default is `2`.