docs(llmagent): correct OutputSchema comment — tools still work via set_model_response

[nuthalapativarun]

Description of Change

Problem:
The comment for OutputSchema in agent/llmagent/llmagent.go incorrectly states that setting OutputSchema prevents the agent from using any tools. This is inaccurate and misleads users into thinking OutputSchema and tools are mutually exclusive.

Solution:
Updated the comment to reflect actual behavior: the framework transparently injects a set_model_response tool when OutputSchema is set, so all tool types (function tools, RAG, agent transfer, etc.) continue to work alongside structured output. See internal/llminternal/outputschema_processor.go for the implementation.

Fixes #756

Testing Plan

Unit Tests:

• I have added or updated unit tests for my change.
• All unit tests pass locally.

Comment-only change; no behavior changes.

$ go test ./agent/llmagent/...
ok  	google.golang.org/adk/agent/llmagent	0.239s

Manual End-to-End (E2E) Tests:

Not applicable — documentation fix only.

Checklist

• I have read the CONTRIBUTING.md document.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have manually tested my changes end-to-end.
• Any dependent changes have been merged and published in downstream modules.

[indurireddy-TF]

Hi @kdroste-google Please review this PR? it's a minor comment update.