ai_screen_context

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

With no annotations, the description carries the behavioral burden, and it discloses what the tool returns (screenshot with grid overlay, accessibility tree with interactive elements, mouse position, frontmost app info). 'Capture a snapshot' implies a non-mutating read, and the enumeration makes the behavior concrete, though it does not mention permission requirements or performance costs.

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 front-loads the core purpose and uses a numbered list to compactly enumerate returns, making the structure easy to parse. The final two sentences earn their place by giving the primary use case and an explicit alternative; no filler or redundant restatement exists.

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?

There is no output schema, so the description compensates by listing all four return categories and their key contents. It covers primary usage and the main alternative, though it does not specify output details such as coordinate formats or tree structure, which are mildly relevant but not essential for invoking the tool correctly.

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?

Schema description coverage is 100%, so the schema already documents all five parameters clearly. The description adds slight semantic alignment (e.g., coordinate grid overlay maps to gridSpacing, accessibility tree maps to maxDepth), but it does not materially increase parameter understanding beyond the schema.

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 opens with 'Capture a comprehensive snapshot of the current screen state for AI analysis', giving a specific verb and resource, then enumerates four concrete return components. It also explicitly differentiates from ai_screen_elements by stating that tool is for clicking, so the agent can distinguish this from an overlapping sibling without inspecting schemas.

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?

It states a clear use case ('Good for understanding screen context') and provides an explicit when-not: 'For CLICKING elements, prefer ai_screen_elements which gives precise coordinates.' This is a direct alternative-selection signal, satisfying the when/when-not/alternative requirement.

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