Scout docs
Connect an agent, make your first call, and find the reference you need.
Read page snapshots
Keep page context focused and use fresh references when the page changes.
Exclude Decorative Elements
Strip decorative elements (icons, separators, generic containers) that add tokens without useful information.
Varies by page — contributes to up to 75% combined reduction with other filters
Exclude Decorative ElementsTYPESCRIPTRole-Based Filtering
Filter the accessibility tree by ARIA roles. Remove roles that aren't relevant to your task — for example, exclude 'img' and 'separator' when extracting text content.
20–40% reduction depending on page structure
Role-Based FilteringTYPESCRIPTDepth Limiting
Limit how deep the accessibility tree is traversed. Shallow depths (2–4) capture top-level navigation and headings. Deeper depths (6–8) capture interactive elements inside nested components.
Configurable — deeper pages benefit most
Depth LimitingTYPESCRIPTElement Scoping
Scope the snapshot to a specific element using a CSS selector. Only the subtree rooted at the matched element is included. Ideal when you know the content region (e.g., 'main', '#content', 'article').
50–75% reduction when scoping to content region
Element ScopingTYPESCRIPTStacked Filtering
Combine multiple filters for maximum reduction. The recommended starting point for most extraction tasks: scope to main content, remove decorative nodes, and limit depth.
Up to 75% combined reduction
Stacked FilteringTYPESCRIPT