@tool | Respan Docs

Overview

The @tool decorator creates a span for a tool operation — a discrete callable used by agents (search, calculator, API call, file read). Tool spans inherit the current entity path and appear nested under the nearest agent, workflow, or task.

1 from respan import tool

Parameters

Parameter	Type	Default	Description
`name`	`str \| None`	Function name	Display name for the tool span.
`version`	`int \| None`	`None`	Version number for the tool.
`method_name`	`str \| None`	`None`	Required when decorating a class. Specifies which method to use as the entry point.
`processors`	`str \| List[str] \| None`	`None`	Route this span to specific named processors. See add_processor.
`export_filter`	`FilterParamDict \| None`	`None`	Filter dict to control which spans are exported. Uses AND logic — all conditions must match.

Function usage

1 from respan import Respan, workflow, task, tool
2 
3 respan = Respan(api_key="your-api-key")
4 
5 @tool(name="web_search")
6 def web_search(query: str):
7     return f"Search results for: {query}"
8 
9 @tool(name="calculator")
10 def calculator(expression: str):
11     return eval(expression)
12 
13 @task(name="research")
14 def research(topic: str):
15     return web_search(topic)
16 
17 @workflow(name="research_workflow")
18 def research_workflow():
19     data = research("Python tracing")
20     count = calculator("2 + 3")
21     return {"data": data, "count": count}
22 
23 print(research_workflow())

Class usage

1 from respan import Respan, agent, tool
2 
3 respan = Respan(api_key="your-api-key")
4 
5 @agent(name="analysis", method_name="run")
6 class Analyzer:
7     @tool(name="tokenize")
8     def tokenize(self, text: str):
9         return text.split()
10 
11     @tool(name="count_words")
12     def count_words(self, text: str):
13         return len(text.split())
14 
15     def run(self):
16         tokens = self.tokenize("respan tracing sdk")
17         count = self.count_words("respan tracing sdk")
18         return {"tokens": tokens, "count": count}
19 
20 print(Analyzer().run())

Notes

Tool spans automatically capture function arguments as input and return values as output
Exceptions inside tools are recorded on the span with error status
Use @tool for operations that agents call, and @task for broader processing steps