From c1560d99fdea0755c5c1466786e7a2137434c74a Mon Sep 17 00:00:00 2001 From: Gaurav Ghosh Date: Mon, 23 Feb 2026 13:29:39 -0800 Subject: [PATCH] fix: update browser agent description to encourage full task delegation Updated the browser_agent description from a primitive-focused listing (navigating, filling, clicking) to a goal-oriented description that emphasizes autonomy, multi-step reasoning, and dynamic feedback interpretation. This encourages the parent agent to delegate entire tasks in a single call rather than micromanaging individual browser actions. --- packages/core/src/agents/browser/browserAgentDefinition.ts | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/packages/core/src/agents/browser/browserAgentDefinition.ts b/packages/core/src/agents/browser/browserAgentDefinition.ts index 8d0f3799c2..e1f733d17e 100644 --- a/packages/core/src/agents/browser/browserAgentDefinition.ts +++ b/packages/core/src/agents/browser/browserAgentDefinition.ts @@ -118,10 +118,7 @@ export const BrowserAgentDefinition = ( kind: 'local', experimental: true, displayName: 'Browser Agent', - description: `Specialized agent for web browser automation using the Accessibility Tree. - Use this agent for: navigating websites, filling forms, clicking buttons, - extracting information from web pages. It can see and interact with the page - structure semantically through the accessibility tree.`, + description: `Specialized autonomous agent for end-to-end web browser automation and objective-driven problem solving. Delegate complete, high-level tasks to this agent — it independently plans, executes multi-step interactions, interprets dynamic page feedback (e.g., game states, form validation errors, search results), and iterates until the goal is achieved. It perceives page structure through the Accessibility Tree, handles overlays and popups, and supports complex web apps.`, inputConfig: { inputSchema: {