> ## Documentation Index
> Fetch the complete documentation index at: https://docs.maadify.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Tool Executions
> Configure execute-tool actions, payloads, loops, and templated inputs
## Add a tool execution
In the parent agent flow, select **Execute tool** and choose a tool.
Use schema fields or a custom JSON payload to build inputs.
Run a test execution to confirm inputs and outputs. Run this in chat to verify inputs and outputs.
## Execute tool configuration
When you add an **execute tool** action, you can control how inputs are built and how the tool runs.
* **Payload type**: schema-driven fields or a custom JSON payload.
* **Access level**: full access or restricted access based on tool defaults. Use will always default with the default tool configurations set on the tool.
* **Async execution**: run the tool in the background, it will use a fire and forget approach.
* **Context memory**: store outputs into memory for agents to access, later or for context management.
* **Schema validation**: surface errors when filling out the payload.
Use schema payloads when you want guardrails. Use custom JSON for advanced mappings.
**Context variable memory configuration**
## Variable templating for tool inputs
Custom payloads and schema values support Jinja-style templating. This lets you map outputs from earlier steps into tool inputs.
### What context variables are available
You can reference:
* **Tool outputs** by tool name and field path.
* **Sub-agent outputs** surfaced through structured outputs or raw message content.
* **Runtime inputs** captured earlier in the workflow, these can be files, trigger inputs, questions, chat history, or current group chat messages.
* **Context variables** carried across all steps these include all tool outputs for all tool execution instances and sub-agent structured outputs.
If you have multiple instances of the same tool, append `__{instance_id}` to the tool name.
### How variables appear in the UI
Use the variable picker to browse and insert values. Variables are grouped by:
* **Tools**: each configured tool output is listed under the tool name.
* **Runtime inputs**: values captured from triggers or previous steps.
* **Structured outputs**: fields saved from sub-agent responses.
If a variable is missing, make sure the tool ran, the step completed, and the output was saved to context.
### Common variable paths
Use these patterns when inserting variables:
* **Tool output**: `{{ tool_key.data.field }}` where tool\_key is the `{tool_name}_{tool_id}`
* **Tool output with instance**: `{{ tool_key__instance_id.data.field }}` where tool\_key is the `{tool_name}_{tool_id}` and instance\_id is the instance id of the tool execution.
* **Nested objects**: `{{ tool_key.data.object.child }}`
* **Arrays**: `{{ tool_key.data.items.0.sku }}` gets the first item in the array.
* **Structured output**: `{{ sub_agent_name_id.key }}` where sub\_agent\_name\_id is the `{sub_agent_name}_{sub_agent_id}`
* **Runtime input**: `{{ input.question }}` gets the question from the runtime input.
* **Inside Loops**: `{{ _loop.property }}` gets the property from each item when the tool is executed in a loop.
Exact variable labels match what you see in the picker. Use the picker to avoid typos.
### Variable syntax
```json theme={null}
{
"order_id": "{{ get_order_99__1.data.id }}",
"customer": "{{ get_order_99__1.data.customer_name }}"
}
```
```json theme={null}
{
"order_id": "{{ get_order__1.data.id }}",
"backup_id": "{{ get_order__2.data.id }}"
}
```
### Nested properties
```json theme={null}
{
"email": "{{ get_customer_99.data.customer.email }}",
"city": "{{ get_customer_99.data.customer.address.city }}"
}
```
### Filters
Use filters to transform values:
* `default` for fallbacks
* `tojson` to serialize objects or lists
* `upper`, `lower`, `trim`
* `length` for counts
* `join` for list formatting
```json theme={null}
{
"note": "{{ order.data.note | default('No notes') }}",
"tags": {{ order.data.tags | default([]) | tojson }},
"email": "{{ user.data.email | lower | trim }}"
}
```
### Conditionals
```json theme={null}
{
"priority": "{% if order.data.total > 100 %}high{% else %}normal{% endif %}"
}
```
### Loops
```json theme={null}
{
"items": [
{% for item in products.data.items %}
{ "sku": "{{ item.sku }}", "qty": {{ item.quantity }} }{% if not loop.last %},{% endif %}
{% endfor %}
]
}
```
Use `tojson` for arrays or objects to keep valid JSON in custom payloads.
## Loops and skip conditions
Execute-tool actions can iterate over arrays and conditionally skip items.
* **Loop on**: select an array path in the tool input.
* **Max iterations**: prevent runaway loops.
* **Fail on error**: stop immediately or continue on errors.
* **Skip conditions**: use all/any groups with nested condition sets. These can be used to skip items in a loop or to skip the tool execution if a condition is met.
