add to docs

Author: icecrasher321

apps/docs/content/docs/en/blocks/agent.mdx

@@ -58,7 +58,7 @@ Controls response randomness and creativity:
 
 ### Max Output Tokens
 
-Controls the maximum length of the model's response. For Anthropic models, Sim uses reliable defaults: streaming executions use the model's full capacity (e.g. 64,000 tokens for Claude 4.5), while non-streaming executions default to 8,192 to avoid timeout issues. For long-form content generation via API, explicitly set a higher value.
+Controls the maximum length of the model's response. For Anthropic models, Sim uses reliable defaults: streaming executions use the model's full capacity (e.g. 64,000 tokens for Claude 4.5), while non-streaming executions default to 8,192 to avoid timeout issues. When using tools with Anthropic models, intermediate tool-calling requests use a capped limit of 8,192 tokens to avoid SDK timeout errors, regardless of your configured max tokens—the final streaming response uses your full configured limit. This only affects Anthropic's direct API; AWS Bedrock handles this automatically. For long-form content generation via API, explicitly set a higher value.
 
 ### API Key