Tap

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

While annotations correctly declare read-only, non-destructive behavior, the description adds no context about behavioral traits such as output format, handling of large DOMs, or the implications of openWorldHint regarding page state dependency.

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?

Extremely terse at four words, but this represents under-specification rather than efficient conciseness. The single sentence fails to earn its place by providing actionable detail for an AI agent.

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 low structural complexity (one optional parameter) and safety annotations, the description is incomplete because it omits critical information about the selector's purpose and gives no indication of the return value format or structure.

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?

With 0% schema description coverage for the 'selector' parameter, the description completely fails to compensate by explaining what the selector is (CSS selector, XPath), its syntax, or the behavior when omitted (full page vs partial).

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?

States the basic action (Get) and target (page DOM structure), but is vague about what 'DOM structure' entails (HTML string, tree object, etc.) and fails to differentiate from siblings like inspect_element or inspect_page which likely overlap in functionality.

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 no guidance on when to use this tool versus the numerous sibling inspection tools (inspect_element, inspect_page, etc.) or what the optional selector parameter implies for scoping the output.

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