BerriAI/litellm · error · HTTPException

Tool '{tool_name}' not found

Error message

Tool '{tool_name}' not found

What it means

Error "Tool '{tool_name}' not found" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/management_endpoints/tool_management_endpoints.py:337

)
async def get_tool_detail(
    tool_name: str,
    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
):
    """
    Get a single tool with its policy overrides (for UI detail view).
    """
    from litellm.proxy.db.tool_registry_writer import get_tool as db_get_tool
    from litellm.proxy.db.tool_registry_writer import list_overrides_for_tool
    from litellm.proxy.proxy_server import prisma_client

    if prisma_client is None:
        raise HTTPException(status_code=500, detail=CommonProxyErrors.db_not_connected_error.value)

    try:
        tool: Final = await db_get_tool(prisma_client=prisma_client, tool_name=tool_name)
        if tool is None:
            raise HTTPException(status_code=404, detail=f"Tool '{tool_name}' not found")
        overrides: Final = await list_overrides_for_tool(prisma_client=prisma_client, tool_name=tool_name)
        return ToolDetailResponse(tool=tool, overrides=overrides)
    except HTTPException:
        raise
    except Exception as e:
        verbose_proxy_logger.exception("Error getting tool detail: %s", e)
        raise HTTPException(status_code=500, detail=str(e))


_ParsedJson: TypeAlias = dict[str, object] | list[object] | str | int | float | bool | None
_PARSED_JSON: Final[TypeAdapter[_ParsedJson]] = TypeAdapter(_ParsedJson)
_STR_OBJECT_DICT: Final = TypeAdapter(dict[str, object])


def _input_snippet_for_tool_log(sl: "_SpendLogRow | None", max_len: int = 200) -> str | None:
    """Short snippet from messages or proxy_server_request for tool usage log row."""
    if sl is None:
        return None

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Verify the tool name exists (list available tools) before querying its spend.

When it happens

Trigger: Thrown at litellm/proxy/management_endpoints/tool_management_endpoints.py:337 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/5a2be6fc90ff4c1a. Report an issue: GitHub.