Add tool calling design documentation

[Furisto]

Explain the core architecture and benefits of Construct's code-based tool calling approach compared to traditional JSON-based systems. Document how agents compose multiple tools, use control flow, and optimize context usage through executable JavaScript.

Key sections:
• How tool calling works in the execution environment • Seven key advantages: composability, control flow, context efficiency,
self-correction, natural for LLMs, reduced overhead, and privacy
• Detailed comparison: JSON vs JavaScript approaches with concrete examples • Research foundation: Wang et al. (2024) ICML findings on code-based agents • When this approach shines: multi-file ops, conditionals, data processing,
exploratory tasks, and complex edits

Includes practical examples showing multi-tool composition, conditional workflows, context-efficient data filtering, and adaptive task execution.

[coderabbitai]

Caution

Review failed

The pull request is closed.

Walkthrough

A new documentation file has been added to the repository that explains tool calling in Construct. The documentation covers how the tool environment is exposed to agents, demonstrates capabilities including composability, control flow, data filtering, and self-correction, provides practical comparisons between JSON-based and code-based approaches, references research foundations, and includes use-case guidance for scenarios such as multi-file operations, conditional workflows, data processing, and exploratory tasks. No changes to code or public APIs were introduced.

---

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Free

📥 Commits

Reviewing files that changed from the base of the PR and between f30c6db and 5492409.

📒 Files selected for processing (1)

• docs/tool_calling.md (1 hunks)

Tip

📝 Customizable high-level summaries are now available in beta!

You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.

• Provide your own instructions using the high_level_summary_instructions setting.
• Format the summary however you like (bullet lists, tables, multi-section layouts, contributor stats, etc.).
• Use high_level_summary_in_walkthrough to move the summary from the description to the walkthrough section.

Example instruction:

"Divide the high-level summary into five sections:

1. 📝 Description — Summarize the main change in 50–60 words, explaining what was done.
2. 📓 References — List relevant issues, discussions, documentation, or related PRs.
3. 📦 Dependencies & Requirements — Mention any new/updated dependencies, environment variable changes, or configuration updates.
4. 📊 Contributor Summary — Include a Markdown table showing contributions:
   | Contributor | Lines Added | Lines Removed | Files Changed |
5. ✔️ Additional Notes — Add any extra reviewer context.
   Keep each section concise (under 200 words) and use bullet or numbered lists for clarity."

Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later.

---

Note

🎁 Summarized by CodeRabbit Free

Your organization is on the Free plan. CodeRabbit will generate a high-level summary and a walkthrough for each pull request. For a comprehensive line-by-line review, please upgrade your subscription to CodeRabbit Pro by visiting https://app.coderabbit.ai/login.

_{Comment @coderabbitai help to get the list of available commands and usage tips.}