Built-in Tools
Core tools provided by decopilot for discovering capabilities and managing work
Overview
Decopilot provides built-in tools that are always available (subject to task/subtask restrictions). These tools enable work management, context access, and agent coordination.
Tool Categories
Discovery & Enablement
Tools for activating capabilities:
- tool_enable - Activate a tool for use in current task
Agent Management
Tools for working with agents:
- agent_search - Find agents configured in the organization
Task Management
Tools for spawning and managing work:
- subtask - Spawn subtask with isolated context
User Interaction
Tools for gathering user input:
- user_ask - Ask user for input or clarification
Context Access
Tools for reading resources and prompts:
- read_resource - Read documentation/guidelines from current scope
- read_prompt - Read prompt templates from current scope
Code Execution & Output
Tools for running code and processing results:
- sandbox - Execute JavaScript code with access to MCP tools
- read_tool_output - Filter large tool outputs using regex patterns
Planning
Tools for structured execution:
- propose_plan - Propose execution plans for user approval
Availability Matrix
| Tool | Task | Subtask | Description |
|---|---|---|---|
tool_enable | ✓ | ✓ | Activate a tool for use in current task |
agent_search | ✓ | ✗ | Find agents configured in the organization |
subtask | ✓ | ✗ | Spawn subtask with fresh context |
user_ask | ✓ | ✗ | Ask user for input or clarification |
read_resource | ✓ | ✓ | Read documentation/guidelines from current scope |
read_prompt | ✓ | ✓ | Read prompt templates from current scope |
sandbox | ✓ | ✓ | Execute JavaScript code with MCP tool access |
read_tool_output | ✓ | ✓ | Filter large tool outputs using regex |
propose_plan | ✓ | ✓ | Propose execution plans for approval |
Tasks are user-initiated and have full access to all built-in tools. Subtasks are spawned by decopilot and have restricted access to prevent infinite delegation and blocking user interactions. Subtasks have a step limit of 15 (vs 30 for tasks) and must return a summary.
Tool discovery: Available scope tools from connected MCP servers are discovered implicitly via the connections listed in the current scope’s Virtual MCP — there is no explicit search tool.
Found an error or want to improve this page?
Edit this page