refactor(agent): improve notebook prompts and add-cell response feedback

[moyiliyi]

Summary

This PR includes two focused improvements to notebook-agent behavior and feedback quality.

1. Prompt instruction refinement for notebook editing/execution workflows.
2. Tool response enhancement to return and surface inserted notebook cell indices.

Motivation

1. In a data analysis and modeling task, the agent followed the prompt by first stating a high-level goal and then proceeding to generate the entire notebook implementation in one pass. For exploratory notebook work, this is not a reasonable default behavior. The notebook instructions should instead encourage incremental analysis, intermediate validation, and task-adaptive planning rather than upfront full-pipeline code generation.

2. add-cell tool actions previously returned generic success responses, which made it harder to reference newly inserted cells in subsequent steps. Returning the inserted cellIndex improves traceability for iterative notebook workflows.

What changed

• Updated NOTEBOOK_EDIT_INSTRUCTIONS to clarify when to prefer exploratory workflows vs. construction workflows.
• Updated NOTEBOOK_EXECUTE_INSTRUCTIONS to encourage smaller, iterative execution cycles for exploratory/scientific tasks.
• Updated notebook add_code_cell and add_markdown_cell command return shape from boolean success to an object containing:
  • cellIndex for the newly inserted cell
• Updated Python tool wrappers (built-in toolsets and Claude tool handlers) to surface the inserted cell index in tool responses when available.