> ## Documentation Index
> Fetch the complete documentation index at: https://docs.contextual.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools Configuration

> Configure tools for agentic workflows in Agent Composer

## Description

Tools configuration defines the tools available to an `AgenticResearchStep`. Each tool requires a name, description, and either `step_config` (for simple tools) or `graph_config` (for complex multi-step tools).

## Tool Definition

Each tool in `tools_config` requires:

| Field          | Description                                       |
| -------------- | ------------------------------------------------- |
| `name`         | Unique identifier for the tool                    |
| `description`  | Description shown to the LLM for tool selection   |
| `step_config`  | Single-step tool configuration                    |
| `graph_config` | Multi-step tool configuration (for complex tools) |

## Using step\_config (Simple Tools)

For tools that map to a single step:

```yaml theme={null}
tools_config:
  - name: search_docs
    description: Search the document datastore for relevant information.
    step_config:
      type: SearchUnstructuredDataStep
      config:
        top_k: 50
        lexical_alpha: 0.1
        semantic_alpha: 0.9
        reranker: "ctxl-rerank-v2-instruct-multilingual-FP8"
        rerank_top_k: 12
        reranker_score_filter_threshold: 0.2
```

## Using graph\_config (Complex Tools)

For tools that require multiple steps:

```yaml theme={null}
tools_config:
  - name: search_and_summarize
    description: Search documents and summarize the results.
    graph_config:
      version: 0.1
      inputs:
        query: str
      outputs:
        summary: str
      nodes:
        search:
          type: SearchUnstructuredDataStep
          config:
            top_k: 20
          input_mapping:
            query: __inputs__#query
        
        summarize:
          type: LanguageModelStep
          config:
            prompt_template: |
              Summarize these search results for the query "{query}":
              {retrievals}
            model_id: "vertex_ai/gemini-2.0-flash"
          input_mapping:
            query: __inputs__#query
            retrievals: search#retrievals
        
        __outputs__:
          type: output
          input_mapping:
            summary: summarize#response
```

## Multiple Tools

You can configure multiple tools for an agent to choose from:

```yaml theme={null}
tools_config:
  - name: search_docs
    description: |
      Search internal documentation. Use for questions about 
      company policies, procedures, and technical guides.
    step_config:
      type: SearchUnstructuredDataStep
      config:
        top_k: 50

  - name: search_web
    description: |
      Search the web for current information. Use for questions
      about external topics, news, or publicly available data.
    step_config:
      type: WebSearchStep
      config:
        model: "gemini-2.5-flash"

  - name: query_database
    description: |
      Query the structured database. Use for questions about
      metrics, statistics, or tabular data.
    step_config:
      type: QueryStructuredDatastoreStep
```

## Tool Descriptions Best Practices

Good tool descriptions help the LLM choose the right tool:

```yaml theme={null}
# Good: Specific about when to use
description: |
  Search the HR policy database. Use this tool for questions about:
  - Employee benefits and compensation
  - Time off and leave policies  
  - Performance review processes
  - Hiring and onboarding procedures

# Bad: Too vague
description: Search for HR stuff.
```

## Recommended Search Config

For `SearchUnstructuredDataStep` tools, these settings provide good baseline performance:

```yaml theme={null}
step_config:
  type: SearchUnstructuredDataStep
  config:
    top_k: 50
    lexical_alpha: 0.1
    semantic_alpha: 0.9
    reranker: "ctxl-rerank-v2-instruct-multilingual-FP8"
    rerank_top_k: 12
    reranker_score_filter_threshold: 0.2
```

## MCP Tools

You can also configure MCP (Model Context Protocol) server tools:

```yaml theme={null}
tools_config:
  - name: crm_search
    description: Search customer records in the CRM system.
    step_config:
      type: MCPClientStep
      config:
        server_url: "https://mcp-server.example.com"
        tool_name: "search_customers"
        tool_args: '{"query": "$query"}'
        auth_headers:
          Authorization: "Bearer ${CRM_API_TOKEN}"
```

## Related

* [Agentic Workflows](/reference/ac-agentic-workflows)
* [Step Reference Catalog](/how-to-guides/ac-yaml-reference)