Add Tool Schema Flatness (TSF) constraint

[tylerpayne]

The "flatness" (i.e. lack of nested structured objects/lists) of a tool's inputSchema can dramatically impact an agent's tool-calling accuracy.

This constraint reports a warning if any of your server's tools have nested inputSchemas.

See: https://composio.dev/blog/gpt-4-function-calling-example

To check flatness, uses the jsonschema library to parse the inputSchema and check for

1. Nested objects
2. Nested arrays
3. Nesting via refs

[Copilot]

Pull Request Overview

Adds a Tool Schema Flatness (TSF) constraint that validates tool input schemas are "flat" without nested objects or arrays. This constraint aims to improve agent tool-calling accuracy by preventing complex nested structures that can confuse agents.

• Added ToolInputSchemaFlatnessConstraint class with comprehensive schema flatness validation
• Integrated the constraint into the existing constraint system with CLI support
• Added comprehensive test coverage for various schema patterns including edge cases

Reviewed Changes

Copilot reviewed 5 out of 6 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
src/mcp_interviewer/constraints/tool_schema_flatness.py	Implements the core constraint logic with nested structure detection and JSON Schema reference resolution
tests/constraints/test_tool_schema_flatness.py	Comprehensive test suite covering flat schemas, nested objects, arrays, references, unions, and edge cases
src/mcp_interviewer/constraints/__init__.py	Registers the new constraint in the constraint system
src/mcp_interviewer/cli.py	Updates CLI help text to include the new TSF constraint code
pyproject.toml	Adds required dependencies for jsonschema and pytest

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}