ceos/fastmcp
1
0
Fork 0
mirror of https://github.com/PrefectHQ/fastmcp.git synced 2026-08-23 22:14:18 +02:00
Code Issues Projects Releases Packages Wiki Activity

Add standalone decorators and eliminate fastmcp.fs module (#2832)

Browse source
This commit is contained in:
Jeremiah Lowin 2026-01-10 12:16:35 -05:00 • committed by GitHub
commit daa2dace2f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
30 changed files with 1280 additions and 1123 deletions
Download patch file Download diff file Expand all files Collapse all files

45
docs/patterns/tool-transformation.mdx
View file

@ -28,16 +28,15 @@ Transformation is also powerful for **environment-aware tools**. You can dynamic
The primary way to create a transformed tool is with the `Tool.from_tool()` class method. At its simplest, you can use it to change a tool's top-level metadata like its `name`, `description`, or `tags`.
In the following simple example, we take a generic `search` tool and adjust its name and description to help an LLM client better understand its purpose.
In the following example, we take a generic `search` tool and adjust its name and description to help an LLM client better understand its purpose.
```python {13-21}
```python {1, 6, 11-19, 22}
from fastmcp.tools import tool, Tool
from fastmcp import FastMCP
from fastmcp.tools import Tool
mcp = FastMCP()
# The original, generic tool
@mcp.tool
# Create a tool without registering it using the standalone @tool decorator
# This creates a Tool object that can be transformed before registration
@tool
def search(query: str, category: str = "all") -> list[dict]:
"""Searches for items in the database."""
return database.search(query, category)
@ -47,39 +46,25 @@ product_search_tool = Tool.from_tool(
search,
name="find_products",
description="""
Search for products in the e-commerce catalog.
Use this when customers ask about finding specific items,
Search for products in the e-commerce catalog.
Use this when customers ask about finding specific items,
checking availability, or browsing product categories.
""",
)
# Only register the transformed version
mcp = FastMCP()
mcp.add_tool(product_search_tool)
```
<Tip>
When you transform a tool, the original tool remains registered on the server. To avoid confusing an LLM with two similar tools, you can disable the original one:
```python
from fastmcp import FastMCP
from fastmcp.tools import Tool
mcp = FastMCP()
# The original, generic tool
@mcp.tool
def search(query: str, category: str = "all") -> list[dict]:
...
# Create a more domain-specific version
product_search_tool = Tool.from_tool(search, ...)
mcp.add_tool(product_search_tool)
# Disable the original tool
search.disable()
```
The standalone `@tool` decorator (from `fastmcp.tools`) creates a Tool object without registering it to any server. This is the recommended approach for tool transformation because:
- You only register the tools you want exposed
- No need to disable or remove the original
- Cleaner separation between tool creation and registration
</Tip>
Now, clients see a tool named `find_products` with a clear, domain-specific purpose and relevant tags, even though it still uses the original generic `search` function's logic.
Now, clients see a tool named `find_products` with a clear, domain-specific purpose, even though it still uses the original generic `search` function's logic.
### Parameters