inspect_ui

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 discloses that the tool inspects UI screenshots for specific categories and can handle multiple images, but does not describe output format, limitations, or side effects (though read-only by nature).

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 two sentences, front-loaded with the core purpose, and every word adds value. No filler.

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?

The tool is relatively simple, and the description covers the input modes (single or multi-image) and the scope of analysis. However, with no output schema, it would benefit from stating what the tool returns, though the inspection context implies a textual report.

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 coverage is 100% with descriptions for image, images, prompt, and mimeType. The description's phrase 'multi-step flow' adds a small nuance to the images parameter, but overall it does not exceed the schema's detail.

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 uses the specific verb 'Inspect' with resource 'UI screenshots' and lists concrete aspects (layout, components, states, copy, errors, UX/accessibility). This clearly distinguishes it from siblings like analyze_image or describe_image, which are more generic image analysis tools.

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 states it accepts 'one screen or a multi-step flow', giving clear input context. It doesn't explicitly mention alternatives or when-not-to-use, but the UI focus implicitly guides selection over generic image tools.

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