ai_web_elements

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

With no annotations, the description carries the behavioral burden. It is upfront about the main side effect ('Auto-launches a CDP-enabled Chrome if needed') and about navigation when a URL is provided. It also clarifies that the result includes screen coordinates intended for mouse_click, giving agents a concrete sense of the output shape. Exact return format and tab-state changes are not disclosed, but the core behaviors are covered.

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 front-loaded with the action and mechanism, and each sentence adds either launch behavior, usage context, or element-type detail. The '[AI-Optimized]' tag is mild filler, and 'ALL interactive elements' overlaps slightly with the later enumeration, but overall it is compact and easily parsed.

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?

For a scan tool with no required parameters and no output schema, the description covers the main inputs, the optional Chrome launch behavior, and the kind of results returned. It would be even stronger with explicit return-structure details and an explicit contrast to ai_screen_elements or accessibility_tree, but an agent has enough context to invoke it 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?

All five parameters already have complete schema descriptions, so the baseline is 3. The description adds little beyond restating URL semantics and emphasizing the coordinate output for mouse_click; it does not clarify cdpPort, tabIndex, includeText, or visibleOnly beyond what the schema already provides.

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?

Describes a specific action ('Scan ALL interactive elements'), a concrete resource ('a web page'), a mechanism ('Chrome DevTools Protocol'), and an output detail ('screen coordinates for mouse_click'). The enumeration of element types makes it clear that this targets DOM/web elements, distinguishing it from screen-based or accessibility-tree sibling 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?

Provides direct invocation guidance: supply a URL to navigate and scan, or omit it to scan the current page, and notes that Chrome will auto-launch if needed. However, it never explicitly says when to choose this tool over close siblings like ai_screen_elements or accessibility_tree, so the comparative usage decision is left to inference.

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