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

# Tool annotations

> Understand the MCP annotation hints each tool declares and how to configure client confirmations.

Every tool in `tools/list` declares all four [MCP tool annotations](https://modelcontextprotocol.io/specification/2025-06-18/server/tools#tool-annotations) so agents and humans can reason about side effects before a call runs.

| Hint | `true` means |
| - | - |
| `readOnlyHint` | Does not modify user data |
| `destructiveHint` | May overwrite, remove, or send (not additive-only) |
| `idempotentHint` | Repeating the call with the same arguments has no further effect |
| `openWorldHint` | Reaches outside Seamless (for example, sends email) |

## Recommended client settings

> [!TIP]
>
> Enable human confirmation for tools with `readOnlyHint: false` in your MCP client, especially those with `destructiveHint: true`. Read-only tools change nothing in your account, but `search_contacts` and `search_companies` still consume credits, so budget for them before running them autonomously.

> [!WARNING]
>
> Destructive tools can overwrite, delete, or send data in ways that cannot be undone. Require explicit approval before calling them.

## Tool reference

Each [tool domain page](https://docs.seamless.ai/mcp/tools/search.md) lists every tool's hints. See [Access control](https://docs.seamless.ai/mcp/access-control.md) for which domains your account can use.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.