refs

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

With no annotations, the description carries the full burden. It discloses that the tool returns interactive elements and a stable handle, and that tab defaults to active tab. However, it does not explain whether the tool is read-only, any side effects, or how the selector/max_items parameters affect behavior. It adds some value but leaves significant behavioral gaps.

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 extremely concise—two sentences—and front-loads the core purpose and output shape. There is no verbose or redundant content; every word adds value.

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 three parameters and no output schema, the description is too brief. It doesn't explain the selector or max_items parameters, how the refs relate to other tools, or what the returned objects contain beyond the tuple structure. This leaves critical gaps for effective usage.

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 schema has three parameters but the description only addresses 'tab' (default behavior). It entirely omits 'selector' and 'max_items', so their meaning and usage are unexplained. Since schema description coverage is 0%, the description fails to compensate for the missing parameter documentation.

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's purpose: it returns interactive elements and stable handles (CDP backendNodeId) as a list of {ref, tag, text}. This is specific and distinguishes it from sibling tools like find_text or get_markdown, as it explicitly returns refs meant for subsequent interactions.

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 minimal guidance: it notes the default behavior when 'tab' is not passed (uses current active tab). However, it gives no hints on when to prefer this tool over alternatives like click_selector or find_text, nor any exclusions or preconditions. The usage context is largely implied by the existence of click_ref siblings.

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