[FEATURE]: Tool-calling optimization for Trinity model family

[mariamjabara]

Feature hasn't been suggested before.

• I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

Add a dedicated system prompt for the Trinity model family to enforce:

• one tool per message
• Use of the question tool when the request is vague
• Avoid repeating the same tool with the same params

Benefits: improved tool-calling reliability and a smoother experience when using Trinity models.

[github-actions]

This issue might be a duplicate or closely related to existing issues addressing model-specific system prompt optimization. Please check:

• [FEATURE]: Add GLM specific system prompt support to better make use of GLM coding plan with it's MCPs. #11730: Add GLM specific system prompt support - directly parallel feature for a different model family
• [FEATURE]: Ability to override tool prompts - create model toolsets #5728: Ability to override tool prompts - create model toolsets
• [FEATURE]: add model identity info to system prompt #9065: Add model identity info to system prompt
• Dynamic system prompts for custom agents #3195: Dynamic system prompts for custom agents
• [BUG] Kimi k2.5 doesn't use the question tool #11053: Kimi k2.5 doesn't use the question tool
• Question tool is way too eager #9525: Question tool is way too eager
• Duplicate Executions in Kimi K2 Model via Cortecs or Nebius Directly #3458: Duplicate Executions in Kimi K2 Model
• Tool Calling Issues with Open Source Models in OpenCode #234: Tool Calling Issues with Open Source Models in OpenCode
• default system prompt materiallly freaks out / degrades reasoning of every high reasoning model #10927: Default system prompt negatively impacts high reasoning models
• [FEATURE]:Support Gemini API by trimming/adapting tool descriptions #9570: Support Gemini API by trimming/adapting tool descriptions

Feel free to ignore if your request addresses a specific gap not covered in these issues.