test(mcp): add eval scenarios for vague and URL-based webpage prompts (refs #940)

Author: madhaviai

scripts/eval_scenarios/fix_webpage_issues_test.ts

@@ -0,0 +1,57 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * Eval scenario: user asks to fix issues with their webpage (no URL given).
+ * When no URL is provided, the model should pick the current frontend and run
+ * and inspect it. Verifies the MCP server is invoked and the model opens the
+ * frontend and inspects it (snapshot, console, or network).
+ *
+ * Note: Tools like performance_start_trace, take_snapshot, list_console_messages,
+ * and list_network_requests do not require a URL in the prompt—they operate on
+ * the currently selected page. Only navigate_page/new_page need a URL to open
+ * a page; the eval runner injects the test URL when htmlRoute is set.
+ */
+
+import assert from 'node:assert';
+
+import type {TestScenario} from '../eval_gemini.ts';
+
+const INSPECTION_TOOLS = [
+  'take_snapshot',
+  'list_console_messages',
+  'list_network_requests',
+];
+
+export const scenario: TestScenario = {
+  prompt: 'Can you fix issues with my webpage?',
+  maxTurns: 4,
+  htmlRoute: {
+    path: '/fix_issues_test.html',
+    htmlContent: `
+      <h1>Test Page</h1>
+      <p>Some content</p>
+      <script>
+        console.error('Intentional error for testing');
+      </script>
+    `,
+  },
+  expectations: calls => {
+    const NAVIGATION_TOOLS = ['navigate_page', 'new_page'];
+    assert.ok(calls.length >= 2, 'Expected at least navigation and one inspection');
+    const navigationIndex = calls.findIndex(c => NAVIGATION_TOOLS.includes(c.name));
+    assert.ok(
+      navigationIndex !== -1,
+      `Expected a navigation call (${NAVIGATION_TOOLS.join(' or ')}), got: ${calls.map(c => c.name).join(', ')}`,
+    );
+    const afterNavigation = calls.slice(navigationIndex + 1);
+    const inspectionCalls = afterNavigation.filter(c =>
+      INSPECTION_TOOLS.includes(c.name),
+    );
+    assert.ok(
+      inspectionCalls.length >= 1,
+      `Expected at least one inspection tool (${INSPECTION_TOOLS.join(', ')}) after navigation, got: ${calls.map(c => c.name).join(', ')}`,
+    );
+  },
+};

scripts/eval_scenarios/frontend_snapshot_test.ts

@@ -0,0 +1,34 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * Eval scenario using "website"/"webpage" wording to verify the model invokes
+ * the right tools when users ask to open a site and read its content.
+ */
+
+import assert from 'node:assert';
+
+import type {TestScenario} from '../eval_gemini.ts';
+
+export const scenario: TestScenario = {
+  prompt:
+    'Open the website at <TEST_URL> and tell me what content is on the page.',
+  maxTurns: 3,
+  htmlRoute: {
+    path: '/frontend_snapshot.html',
+    htmlContent: '<h1>Frontend Test</h1><p>This is a test webpage.</p>',
+  },
+  expectations: calls => {
+    assert.strictEqual(calls.length, 2);
+    assert.ok(
+      calls[0].name === 'navigate_page' || calls[0].name === 'new_page',
+      'First call should be navigation',
+    );
+    assert.strictEqual(
+      calls[1].name,
+      'take_snapshot',
+      'Second call should be take_snapshot to read page content',
+    );
+  },
+};

src/tools/pages.ts

@@ -80,7 +80,8 @@ export const closePage = defineTool({
 
 export const newPage = defineTool({
   name: 'new_page',
-  description: `Creates a new page`,
+
+  description: `Open a new tab and load a URL. If no URL given, ask to run from current directory or for the URL.`,
   annotations: {
     category: ToolCategory.NAVIGATION,
     readOnlyHint: false,
@@ -113,7 +114,7 @@ export const newPage = defineTool({
 
 export const navigatePage = defineTool({
   name: 'navigate_page',
-  description: `Navigates the currently selected page to a URL.`,
+  description: `Go to a URL, or back, forward, or reload. If no URL given, ask to run from current directory or for the URL.`,
   annotations: {
     category: ToolCategory.NAVIGATION,
     readOnlyHint: false,