Did you expect it to be good at it?
Humans also don't give a perfect 1/n probability when asked for a random number.
Humans give way more random answers than LLMs to questions like "give me a random number between 1-100" (when not giving the LLM any tool calls).
Humans give way more random answers than LLMs to questions like "give me a random number between 1-100" (when not giving the LLM any tool calls).