diff --git a/docs/edge/en/tools/search-research/tavilyresearchtool.mdx b/docs/edge/en/tools/search-research/tavilyresearchtool.mdx
index 34fdc8c66..d58b09204 100644
--- a/docs/edge/en/tools/search-research/tavilyresearchtool.mdx
+++ b/docs/edge/en/tools/search-research/tavilyresearchtool.mdx
@@ -63,11 +63,12 @@ print(crew.kickoff())
 
 ## Configuration Options
 
-The `TavilyResearchTool` accepts the following arguments — all can be set on the tool instance (defaults for every call) or per-call via the agent's tool input:
+The `TavilyResearchTool` accepts the following arguments. Set `model`, `tavily_output_schema`, `stream`, and `citation_format` on the tool instance as defaults; pass `input`, `model`, `output_schema`, `stream`, and `citation_format` per call via the agent's tool input:
 
 - `input` (str): **Required.** The research task or question to investigate.
 - `model` (Literal["mini", "pro", "auto"]): The Tavily research model. `"auto"` lets Tavily pick; `"mini"` is faster/cheaper; `"pro"` is the most capable. Defaults to `"auto"`.
-- `output_schema` (dict | None): Optional JSON Schema that structures the research output. Useful when you want strictly typed results.
+- `output_schema` (dict | None): Optional per-call JSON Schema that structures the research output. Useful when you want strictly typed results.
+- `tavily_output_schema` (dict | None): Optional default JSON Schema for Tavily research output when the tool is instantiated.
 - `stream` (bool): When `True`, the tool returns an iterator of SSE chunks emitting research progress and the final result instead of a single string. Defaults to `False`.
 - `citation_format` (Literal["numbered", "mla", "apa", "chicago"]): Citation format for the report. Defaults to `"numbered"`.
 
@@ -97,7 +98,7 @@ for chunk in tavily_tool.run(input="Summarize recent advances in retrieval-augme
 
 ### Structured output via JSON Schema
 
-Pass an `output_schema` when you need a typed result instead of a free-form report:
+Pass an `output_schema` per call, or set `tavily_output_schema` on the tool instance, when you need a typed result instead of a free-form report:
 
 ```python
 output_schema = {
@@ -110,7 +111,7 @@ output_schema = {
     "required": ["summary", "key_points", "sources"],
 }
 
-tavily_tool = TavilyResearchTool(output_schema=output_schema)
+tavily_tool = TavilyResearchTool(tavily_output_schema=output_schema)
 ```
 
 ## Features
diff --git a/lib/crewai-tools/src/crewai_tools/tools/tavily_research_tool/tavily_research_tool.py b/lib/crewai-tools/src/crewai_tools/tools/tavily_research_tool/tavily_research_tool.py
index 084fefdf1..d13c804bc 100644
--- a/lib/crewai-tools/src/crewai_tools/tools/tavily_research_tool/tavily_research_tool.py
+++ b/lib/crewai-tools/src/crewai_tools/tools/tavily_research_tool/tavily_research_tool.py
@@ -63,7 +63,7 @@ class TavilyResearchTool(BaseTool):
         default="auto",
         description="Default model used for new Tavily research tasks.",
     )
-    output_schema: dict[str, Any] | None = Field(
+    tavily_output_schema: dict[str, Any] | None = Field(
         default=None,
         description="Default JSON Schema used to structure research output.",
     )
@@ -87,6 +87,10 @@ class TavilyResearchTool(BaseTool):
     )
 
     def __init__(self, **kwargs: Any):
+        output_schema = kwargs.get("output_schema")
+        if isinstance(output_schema, dict) and "tavily_output_schema" not in kwargs:
+            kwargs["tavily_output_schema"] = kwargs.pop("output_schema")
+
         super().__init__(**kwargs)
         if TAVILY_AVAILABLE:
             api_key = os.getenv("TAVILY_API_KEY")
@@ -152,7 +156,7 @@ class TavilyResearchTool(BaseTool):
         result = self._client.research(
             input=input,
             model=self.model if model is None else model,
-            output_schema=self.output_schema
+            output_schema=self.tavily_output_schema
             if output_schema is None
             else output_schema,
             stream=use_stream,
@@ -185,7 +189,7 @@ class TavilyResearchTool(BaseTool):
         result = await self._async_client.research(
             input=input,
             model=self.model if model is None else model,
-            output_schema=self.output_schema
+            output_schema=self.tavily_output_schema
             if output_schema is None
             else output_schema,
             stream=use_stream,