browser_get_dom

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

With no annotations, the description carries the full burden of behavioral disclosure. It lists exactly what is extracted (forms, links, scripts, iframes, comments, event handlers, data-* attributes, simplified DOM tree), explains the effect of max_depth on token usage, and states the prerequisite. This gives a thorough understanding of the tool's behavior without needing to invoke it.

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 well-organized with clear sections: purpose, prerequisite, extracted items, usage, and args. It is somewhat long but every section adds value, especially the detailed list of extracted data elements. It could be more concise, but the structure enhances readability.

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 description covers prerequisites, the exact data extracted, parameter defaults, and a use case. An output schema is present, so return values need not be described. It lacks error-handling details or edge cases (e.g., what happens if selector not found), but for a DOM extraction tool with moderate complexity, it is adequately complete.

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 0%, so the description must compensate. It explains selector (root element CSS selector), max_depth (depth of traversal and token trade-off), and session_name (browser session), but omits tab_id entirely. This is a slight gap, but the provided parameter details go beyond the schema's basic type/default information.

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 extracts security-relevant DOM structure with a specific verb ('Extract') and resource ('DOM structure from the current page'). It distinguishes from sibling tools like browser_get_text or browser_js by focusing on security-relevant elements such as forms, CSRF tokens, scripts, and comments.

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 explicitly states when to use it ('initial recon after navigating to a page') and provides a prerequisite ('browser_open and browser_go must have been called first'). It also contrasts with the proxy by noting it returns data the proxy cannot see, but it does not name alternative tools or when not to use this tool.

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