fix: enable optional parameters in use_aws to prevent KeyError

[jwliu36]

Description

Make parameters optional in the use_aws tool to prevent a KeyError when the LLM omits it.

Some AWS operations like list_buckets don't require parameters. When using non-Bedrock models (e.g., OpenAI GPT-4o), the LLM often omits the parameters field entirely, causing a crash at tool_input["parameters"].

Changes:

• Use tool_input.get("parameters", {}) instead of tool_input["parameters"]
• Remove parameters from the required list in TOOL_SPEC
• Add unit test for calling use_aws without parameters

Related Issues

Fixes #332

Documentation PR

N/A

Type of Change

Bug fix

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature
• My changes generate no new warnings
• Any dependent changes have been merged and published

---

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.