Clarify that sampling temperature ranges depend on providers

Co-authored-by: Cliff Hall <[email protected]>

Author: LucaButBoring

docs/specification/draft/client/sampling.mdx

@@ -246,7 +246,7 @@ accordingly.
 
 LLM sampling can be fine-tuned with the following parameters:
 
-- `temperature`: Controls randomness in model responses. Higher values produce higher randomness, and lower values produce more stable output.
+- `temperature`: Controls randomness in model responses. Higher values produce higher randomness, and lower values produce more stable output. Valid range depends upon the model provider.
 - `maxTokens`: Maximum tokens to generate; required.
 - `stopSequences`: Array of sequences that stop generation.
 - `metadata`: Additional provider-specific parameters.