Stop Over-Prompting: OpenAI’s New GPT-5.6 Guidelines Change Everything

OpenAI's new GPT-5.6 Sol prompting guide reports internal tests where lean system prompts improved evaluation scores by 10-15% while cutting tokens by 41-66% and costs by 33-67%. The guide introduces a first-ever Programmatic Tool Calling section and the text.verbosity API parameter, both absent from the GPT-5 playbook.