dograh/docs/voice-agent/tools/introduction.mdx

---
title: "Tools"
description: "Extend your voice agent's capabilities by giving it tools to perform actions during live conversations."
---

Tools let your AI agent take actions during a conversation — transfer calls, end calls, call external APIs, or invoke remote MCP servers — based on the context of the conversation and your prompt instructions.

When a tool is attached to a workflow node, the LLM decides **when** to invoke it and **what parameters** to pass, based on the user's spoken intent and your node-level instructions.

## Tool Types

Dograh provides two categories of tools:

### Built-in Tools

Pre-configured tools that handle common telephony operations out of the box:

- [**Call Transfer**](/voice-agent/tools/call-transfer) — Transfer the active call to a phone number or SIP endpoint
- [**End Call**](/voice-agent/tools/end-call) — Terminate the call when the conversation is complete

### Custom Tools

Tools you define to integrate with any external system:

- [**HTTP API**](/voice-agent/tools/http-api) — Call any REST API endpoint during a conversation (e.g., CRM updates, data lookups, triggering automations)
- [**MCP Tool**](/voice-agent/tools/mcp-tool) — Connect an external MCP server and expose its remote tools to the LLM during a conversation

## How Tools Work

1. You **define** a tool with a name, description, and parameters
2. You **attach** the tool to one or more workflow nodes
3. During a call, the LLM reads your node prompt, the tool description, and the caller's intent to decide whether to invoke the tool
4. The tool executes and returns a result that the agent can use to continue the conversation

## Best Practices

- **Attach only relevant tools to each node** — fewer tools means more reliable invocations
- **Write clear tool descriptions** — the LLM uses these to decide when to call the tool
- **Guide the LLM in your node prompt** — explicitly describe when a tool should be used
- **Test tool behavior** — verify your agent invokes tools at the right moments using web or phone calls
feat: add pre call fetch configuration (#222) * feat: add pre call fetch configuration * docs: add NEW tags for pages about new features --------- Co-authored-by: Sabiha Khan <sabihak89@gmail.com> 2026-04-06 12:30:37 +05:30			`---`
			`title: "Tools"`
			`description: "Extend your voice agent's capabilities by giving it tools to perform actions during live conversations."`
			`---`

feat(mcp): generic MCP tool source with per-node function filtering (#301) * feat(mcp): generic MCP tool source with per-node function filtering Adds a Model Context Protocol tool category: connect a customer MCP server and expose its tools to the agent, with optional per-node allow-listing of individual MCP functions. - ToolCategory.MCP enum + alembic migration - MCP definition validator and collision-safe function-name namespacing - McpToolSession wrapper: graceful-degrade, per-call open/close lifecycle - CustomToolManager MCP branch (schemas + proxy handlers) - Per-node mcp_tool_filters threaded through DTO/graph/engine - Best-effort discovered_tools catalog cache + POST /tools/{uuid}/mcp/refresh - UI: MCP create/edit config, tabbed ToolSelector with per-node toggles * feat: refactor for code standardisation and documentation --------- Co-authored-by: Abhishek Kumar <abhishek@a6k.me> 2026-05-19 07:40:00 -03:00			`Tools let your AI agent take actions during a conversation — transfer calls, end calls, call external APIs, or invoke remote MCP servers — based on the context of the conversation and your prompt instructions.`
feat: add pre call fetch configuration (#222) * feat: add pre call fetch configuration * docs: add NEW tags for pages about new features --------- Co-authored-by: Sabiha Khan <sabihak89@gmail.com> 2026-04-06 12:30:37 +05:30
			`When a tool is attached to a workflow node, the LLM decides when to invoke it and what parameters to pass, based on the user's spoken intent and your node-level instructions.`

			`## Tool Types`

			`Dograh provides two categories of tools:`

			`### Built-in Tools`

			`Pre-configured tools that handle common telephony operations out of the box:`

			`- [Call Transfer](/voice-agent/tools/call-transfer) — Transfer the active call to a phone number or SIP endpoint`
			`- [End Call](/voice-agent/tools/end-call) — Terminate the call when the conversation is complete`

			`### Custom Tools`

			`Tools you define to integrate with any external system:`

			`- [HTTP API](/voice-agent/tools/http-api) — Call any REST API endpoint during a conversation (e.g., CRM updates, data lookups, triggering automations)`
feat(mcp): generic MCP tool source with per-node function filtering (#301) * feat(mcp): generic MCP tool source with per-node function filtering Adds a Model Context Protocol tool category: connect a customer MCP server and expose its tools to the agent, with optional per-node allow-listing of individual MCP functions. - ToolCategory.MCP enum + alembic migration - MCP definition validator and collision-safe function-name namespacing - McpToolSession wrapper: graceful-degrade, per-call open/close lifecycle - CustomToolManager MCP branch (schemas + proxy handlers) - Per-node mcp_tool_filters threaded through DTO/graph/engine - Best-effort discovered_tools catalog cache + POST /tools/{uuid}/mcp/refresh - UI: MCP create/edit config, tabbed ToolSelector with per-node toggles * feat: refactor for code standardisation and documentation --------- Co-authored-by: Abhishek Kumar <abhishek@a6k.me> 2026-05-19 07:40:00 -03:00			`- [MCP Tool](/voice-agent/tools/mcp-tool) — Connect an external MCP server and expose its remote tools to the LLM during a conversation`
feat: add pre call fetch configuration (#222) * feat: add pre call fetch configuration * docs: add NEW tags for pages about new features --------- Co-authored-by: Sabiha Khan <sabihak89@gmail.com> 2026-04-06 12:30:37 +05:30
			`## How Tools Work`

			`1. You define a tool with a name, description, and parameters`
			`2. You attach the tool to one or more workflow nodes`
			`3. During a call, the LLM reads your node prompt, the tool description, and the caller's intent to decide whether to invoke the tool`
			`4. The tool executes and returns a result that the agent can use to continue the conversation`

			`## Best Practices`

			`- Attach only relevant tools to each node — fewer tools means more reliable invocations`
			`- Write clear tool descriptions — the LLM uses these to decide when to call the tool`
			`- Guide the LLM in your node prompt — explicitly describe when a tool should be used`
			`- Test tool behavior — verify your agent invokes tools at the right moments using web or phone calls`