browser_query_selector

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

With no annotations, the description carries the burden. It discloses automatic iframe piercing, return fields (backendNodeIds, text, bounding boxes), and implies non-destructive read. Minor missing details (e.g., behavior on missing element) but overall adequate.

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?

Four focused sentences with no redundancy. Core function, frame piercing, usage guidance, and integration hint for atomic_interact are each addressed concisely.

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?

Despite no output schema, the description sufficiently explains return values and behavior (iframe piercing). For a query tool with well-defined parameters, it covers all needed context.

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%, so baseline 3. Description adds marginal value by reinforcing XPath prefix usage but does not add significant new meaning 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 clearly states the tool queries the DOM using CSS or XPath and returns matching elements with backendNodeIds, text, and bounding boxes. It also mentions automatic iframe piercing, distinguishing it from siblings like get_semantic_surface.

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?

Explicitly advises preferring get_semantic_surface for page understanding and specifies this tool for CSS selectors not surfaced by the AX tree. Also notes returned backendNodeIds can be used with atomic_interact, providing clear when-to-use and alternatives.

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