Validation for allowed tool parameters.

[sangee2004]

Steps to reproduce the problem:
Scenario 1:

1. Execute the following script that has invalid tool parameter - aaa: true in the script.

aaa: true
Tools: Bob

Ask Bob how he is doing and let me know exactly what he said.

---
Name: Bob
Description: I'm Bob, a friendly guy.
Args: question: The question to ask Bob.

When asked how I am doing, respond with "Thanks for asking "${Question}", I'm doing great fellow friendly AI tool!"

This results in the user message for chat completion call made to become incorrect and we get output like I'm sorry, but I'm unable to interact with or ask questions to real people or characters named Bob as I am a text-based AI with no capability to communicate outside this platform

Scenario 2:

1. Execute the following script that has invalid tool parameter - aaa: true in the script but have it set below the Tools: line

Tools: Bob
aaa: true

Ask Bob how he is doing and let me know exactly what he said.

---
Name: Bob
Description: I'm Bob, a friendly guy.
Args: question: The question to ask Bob.

When asked how I am doing, respond with "Thanks for asking "${Question}", I'm doing great fellow friendly AI tool!"

In this case , he invalid argument is ignored completely and script gets executed successfully.

Expected Behavior:
In both these cases , ideally we expect to see a parser error and fail even before any chat completion calls are made.