fix(tools/bigquery-execute-sql): avoid surfacing invalid queries as MCP 500s

[jack-larch]

Description

Route bigquery-execute-sql dry-run validation failures through the shared GCP error processor instead of hardcoding them as internal server errors.

This keeps normal BigQuery query mistakes in the tool-error path rather than escalating them into MCP transport failures.

PR Checklist

• Make sure you reviewed CONTRIBUTING.md
• Make sure to open an issue as a bug/issue before writing your code! That way we can discuss the change, evaluate designs, and agree on the general idea
• Ensure the tests and linter pass
• Code coverage does not decrease (if any source code was changed)
• Appropriate docs were updated (if necessary)
• Make sure to add ! if this involve a breaking change

Notes:

• I could not run go test locally in this environment because the Go toolchain is not installed on this machine.
• I added a focused regression test around ProcessGcpError so the intended classification is explicit in CI.

🛠️ Fixes #3055

Made with Cursor

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Code Review

This pull request updates the BigQuery SQL execution tool to use a centralized GCP error processing utility, util.ProcessGcpError, instead of a generic internal server error for query validation failures. Additionally, it introduces unit tests for ProcessGcpError to ensure correct mapping of GCP errors to AgentError or ClientServerError based on status codes and error reasons. I have no feedback to provide.

[duwenxin99]

@jack-larch Thanks for opening the PR! Could you make sure to sign the CLA? Thanks!

[duwenxin99]

/gcbrun

[duwenxin99]

/gcbrun