---

name: cintegrity-secure-tool-execution description: Use when search_tools, execute_tool, or execute_workflow tools are available. For multi-step operations, use execute_workflow with proper imports.

cintegrity Tool Execution

Available Tools

• search_tools(query) - Find tools and their schemas
• execute_tool(tool_name, args) - Execute single tool
• execute_workflow(planner_code) - Execute Python workflow

Workflow Structure

Copyfrom cintegrity.mcp_tools.<server> import <tool_name>

async def workflow():
    result = await <tool_name>(arg=value)
    return result

Rules

1. Entry point: async def workflow():
2. Use await for tool calls
3. Keyword arguments: tool(arg=value)
4. Tools return values directly

Return Value Handling

Scalars (int, str, bool): Assign directly to variables

Copycount = await add(a=10, b=5)        # Returns: 15
total = await multiply(a=count, b=2) # Returns: 30

Objects (dict): Access fields by name

Copyuser = await get_user(id=123)  # Returns: {"name": "Alice", "age": 30}
name = user["name"]
age = user["age"]

User Input: Request values with elicit()

Copyc = await elicit(message="Enter value:", response_type=int)  # Returns: 42
result = await compute(a=10, b=c)

Complete Example

Copyfrom cintegrity.mcp_tools.database import get_user, update_score

async def workflow():
    # Get user data (returns dict)
    user = await get_user(user_id=123)
    current_score = user["score"]

    # Request bonus points
    bonus = await elicit(message="Enter bonus points:", response_type=int)

    # Calculate new score (scalar)
    new_score = await update_score(user_id=123, score=current_score + bonus)

    return {"user": user["name"], "new_score": new_score}