Skip to content

compose_request_details

Add detail to the NEXT snapshot only (all elements), then revert to the compact list. - BOUNDS: {x,y,w,h} per element, for spatial reasoning or telling similar elements apart.

Source

  • Kind: class-backed
  • Class: xyz.block.trailblaze.compose.driver.tools.ComposeRequestDetailsTool

Contract

  • Visible to LLM: yes (surface_to_llm: true)
  • Recordable: no (is_recordable: false)
  • Host-only: no (requires_host: false)

Input schema

Required parameters

  • include — array<enum(BOUNDS)> Detail types to include.

Output

Returns: string (opaque text content)

Typed result schemas (kind: query | action, MCP structuredContent) are not yet carried by the resolved manifest — this section will gain detail when that lands.