[Md. Shalah Uddin (shanto462)]

Motivation & Context

FunctionTool.to_dict() left out the parameter schema of tools declared with a JSON schema dict (MCP server tools, AG-UI client tools, vector store tools and others). Since #3907 these tools keep self.input_model = None, and to_dict() skipped input_model whenever it was empty. After from_dict() the tool declared different or empty parameters.

Description & Review Guide

• What are the major changes? to_dict() now writes input_model from parameters() for every tool, unless the caller excludes input_model. A regression test, with and without a function, checks that to_dict() contains the schema and that from_dict() restores the same parameters().
• What is the impact of these changes? Serialized dict-schema tools include their schema, so a restored tool declares the same parameters. The output for Pydantic-model and signature-based tools does not change, and exclude={"input_model"} still omits the key.
• What do you want reviewers to focus on? I removed the not self.input_model condition instead of adding a _schema_supplied check. input_model is None only for dict-schema tools; every other tool gets a Pydantic model (passed in, inferred from the function, or an empty generated model). So the condition had no other effect.

Related Issue

Fixes #9296

No other open PR covers this issue.

AI Assistance

• No material AI assistance was used.
• This is an AI-assisted contribution. I reviewed, understood, and verified all submitted content and accept responsibility for it.

AI assistance details: issue analysis, implementation, tests, and this PR description.

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR links to an agreed issue with no competing open PR, or the Related Issue section documents a trivial-change or repository-automation exception.
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

[Copilot]

🟢 Approval recommended

The focused change correctly resolves the reported serialization regression with appropriate coverage.

0 open findings

What changed in this PR

Fixes schema loss when serializing and restoring dict-schema FunctionTool instances.

Changes:

• Always serializes tool parameters unless explicitly excluded.
• Adds regression coverage for executable and declaration-only tools.

File	Description
python/​packages/​core/​agent_framework/​_tools.py	Preserves dict-based input schemas during serialization.
python/​packages/​core/​tests/​core/​test_tools.py	Verifies schema-preserving round trips.

🧠 Review effort: Balanced

---

💡 Add a code-review agent skill for context-aware, tailored reviews. Learn more in the docs.