> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/relay/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# nemo_relay.tools

> Tool lifecycle helpers.

Generated from `python/nemo_relay/tools.py`.

Module `nemo_relay.tools`.

Tool lifecycle helpers.

## Functions

### `call`

```python
def call(name, args, *, handle = None, attributes = None, data = None, metadata = None, tool_call_id = None, timestamp: datetime | None = None)
```

Start a manual tool span and return its `ToolHandle`.

### `call_end`

```python
def call_end(handle, result, *, data = None, metadata = None, timestamp: datetime | None = None)
```

Finish a manual tool span started by `call()`.

### `execute`

```python
def execute(name, args, func, *, handle = None, attributes = None, data = None, metadata = None)
```

Run a tool through the managed middleware pipeline.

### `request_intercepts`

```python
def request_intercepts(name, args)
```

Apply global tool request intercepts to `args`.

### `conditional_execution`

```python
def conditional_execution(name, args)
```

Run tool conditional-execution guardrails for `args`.