Analyze Screen (AI) [Pro]

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It indicates the tool is read-only (analysis), which is a key behavioral trait. It mentions 'uses AI vision', implying it may have latency or require API access, but does not disclose potential costs, rate limits, or that it might fail on non-visual screens. A 3 is appropriate for covering the basic safety profile without deeper details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at two sentences, front-loading the purpose and listing return elements effectively. One minor issue: the word 'structured' could be replaced with more specificity, but overall it's well-structured and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's single parameter and no output schema, the description provides a reasonable overview of what the tool returns. It mentions 'app name, screen type, interactive elements with coordinates, visible text, and suggested next actions', which helps the agent understand the tool's capabilities without needing an output schema. Some details like the exact format of coordinates or whether the output is deterministic could enhance completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage on the single required parameter 'device_id', which is well-described. The description does not add any additional context about the parameter beyond the schema, but since coverage is high, the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool uses AI vision to analyze a mobile device's screen, returning a structured analysis with specific elements like app name, screen type, interactive elements, and suggested actions. It distinguishes itself from siblings as 'the primary tool for understanding what is currently displayed on the device', which contrasts with more specific tools like extract_text, find_element, or take_screenshot.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool ('analyze the current screen') and implies it's the primary tool, suggesting it should be used before more specific tools. However, it does not explicitly state when not to use it or mention alternatives like get_screen_size or get_ui_elements.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.