feat(agents): Update screenshots & improve descriptions (#15914)

closes
https://linear.app/getsentry/issue/TET-1655/update-agent-monitoring-screenshots-for-ui2

Author: priscilawebdev

docs/product/insights/ai/agents/dashboard.mdx

@@ -5,33 +5,50 @@ description: Learn how to use Sentry's AI Agents Dashboard.
 og_image: /og-images/product-insights-ai-agents-dashboard.png
 ---
 
-Once you've [configured the Sentry SDK](/product/insights/ai/agents/getting-started/) for your AI agent project, you'll start receiving data in the Sentry [AI Agents Insights](https://sentry.io/orgredirect/organizations/:orgslug/insights/ai/agents/) dashboard.
+The [AI Agents Insights](https://sentry.io/orgredirect/organizations/:orgslug/insights/ai/agents/) dashboard provides a comprehensive view of your AI workflows, including executions, model costs and token usage, tool calls, and recent errors. After you've [configured the Sentry SDK](/product/insights/ai/agents/getting-started/) in your project, telemetry data is collected and displayed in the dashboard to support analysis of system behavior and performance.
 
-The main dashboard provides a comprehensive view of all your AI agent activities, performance metrics, and recent executions.
+At the top of the page, you will be able to navigate between the three tabs: [Overview](#overview), [Models](#models) and [Tools](#tools).
 
-![AI Agents Monitoring Overview](./img/overview.png)
+## Overview
 
-The dashboard displays key widgets like:
+The Overview tab is the landing page for monitoring your AI workflows:
+
+![AI Agents Monitoring Overview](./img/overview-tab.png)
+
+The dashboard displays the following key widgets:
 
 - **Traffic**: Shows agent runs over time, error rates, and releases to track overall activity and health
 - **Duration**: Displays response times for your agent executions to monitor performance
 - **Issues**: Highlights recent errors and problems that need attention, including agent failures and exceptions
+- **LLM Calls**: Count of LLM generations over time
+- **Tokens Used**: Token usage by top models
+- **Tool Calls**: Tool call volume and trends
+
+Below these widgets is a traces table with detailed distribution information:
+
+![AI Agent Trace Table](./img/trace-table-detailed-distribution.png)
+
+Click on any trace to open the [abbreviated trace view](#abbreviated-trace-view) in a drawer.
+
+## Models
+
+The Models tab displays Model Cost, Tokens Used, and Token Types widgets, as well as all used models with durations and token usage:
+
+![AI Agents Monitoring Models](./img/models-tab.png)
+
 
-Underneath these widgets are three segments that offer focused widgets and a detailed distribution table:
+## Tools
 
-- **Traces**: LLM Calls, Tokens Used, and Tool Calls widgets, as well as recent agent runs with duration, errors, number of LLM and tool calls, and token usage
-- **Models**: Model Cost, Tokens Used, and Token Types widgets, as well as all used models with durations and token usage
-- **Tools**: Tool Calls and Tool Errors widgets, as well as all used tools with durations and errors
+The Tools tab displays Tool Calls and Tool Errors widgets, as well as all used tools with durations and errors:
 
-![AI Agent Trace Table](./img/trace-table.png)
+![AI Agents Monitoring Tools](./img/tools-tab.png)
 
-Click on any trace to open the abbreviated trace view in a drawer.
 
 ## Abbreviated Trace View
 
 Opens as a drawer when clicking any trace, showing essential details:
 
-![AI Agent Abbreviated Trace View](./img/abbreviated-trace-view.png)
+![AI Agent Abbreviated Trace View](./img/abbreviated-trace-view-drawer.png)
 
 - **Agent Invocations**: Each agent execution and nested calls
 - **LLM Generations**: Language model interactions with token breakdown
@@ -46,7 +63,7 @@ Click **"View in full trace"** for comprehensive debugging details.
 
 Shows complete agent workflow with full context:
 
-![AI Agent Detailed Trace View](./img/trace-view.png)
+![AI Agent Detailed Trace View](./img/full-trace-view.png)
 
 This detailed view reveals: