diff --git a/spiceaidocs/docs/features/ai-gateway/runtime_tools.md b/spiceaidocs/docs/features/ai-gateway/runtime_tools.md
index 5d0d80a5..0996741b 100644
--- a/spiceaidocs/docs/features/ai-gateway/runtime_tools.md
+++ b/spiceaidocs/docs/features/ai-gateway/runtime_tools.md
@@ -21,8 +21,22 @@ models:
       spice_tools: auto # Use all available tools
 ```
 
+### Tool Recursion Limit
+When a model requests to call a runtime tool, Spice runs the tool internally and feeds it back to the model. The `tool_recursion_limit` parameter limits the depth of internal recursion Spice will undertake. By default, Spice can infinitely recurse if the model requests to do so. 
+
+```yaml
+models:
+ - name: my-model
+   from: openai
+   params:
+     tool_recursion_limit: 3
+```
+
 ## Available tools
  - `list_datasets`: List all available datasets in the runtime.
  - `sql`: Execute SQL queries on the runtime.
  - `table_schema`: Get the schema of a specific SQL table.
  - `document_similarity`: For datasets with an embedding column, retrieve documents based on an input query. It is equivalent to [/v1/search](/api/http/search).
+ - `sample_distinct_columns`: For a dataset, generate a synthetic sample of data whereby each column has at least a number of distinct values.
+ - `random_sample`: Sample random rows from a table.
+ - `top_n_sample`: Sample the top N rows from a table based on a specified ordering.