domains / families / agent-tooling / toolkit-research

toolkit-research

separate

Use when the user explicitly requests research with Baizhi Agent Toolkit. Discover the connected MCP tools and their current schemas, agree a request budget, and produce a sourced result without exposing credentials.

When to use

• research with Baizhi Agent Toolkit
• discover connected MCP tools
• inspect tool schemas
• agree request budget
• produce sourced result

When not to use

• tasks that merely mention research
• asking for API keys in chat
• printing credentials
• placing keys in command arguments
• reading unrelated credential files
• inventing tool names
• assuming capabilities exist
• representing service as read-only, free, or locally hosted

Skill page

Source