scan_page

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

With no annotations provided, the description carries the behavioral burden. It usefully indicates a read-only operation, that the real browser session/login state is preserved, and that output is simplified HTML/text with defaults and timeout. However, it does not disclose potential side effects, how extra_js is executed, or what 'simplified' means in terms of content fidelity.

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 concise and front-loaded, with the primary purpose in the first sentence and defaults in the second. It avoids filler and repetitive content. It could earn a 5 if it used the remaining space to clarify parameter semantics, but as written it is efficient despite being under-specified elsewhere.

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 the tool has 7 parameters, no annotations, and 0% schema description coverage, the description is not complete enough. The output schema covers return shape, but the many undocumented parameters and lack of usage guidance leave significant gaps. An agent cannot confidently decide when to use this tool or how to configure it beyond defaults.

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, but it only restates defaults for three of seven parameters without explaining their meaning. Parameters like extra_js, text_only, session_id, and instruction remain completely unexplained. The description adds a few hints like 'timeout=15 seconds' but is far from sufficient for correct parameter use.

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 a specific action ('Read the current page') and a specific result ('simplified HTML/text'), which distinguishes it from visual tools like capture_page_screenshot and from execute_js. The mention of preserving login state adds meaningful context. This is a clear, non-tautological purpose statement.

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 gives no explicit guidance on when to prefer scan_page over alternatives such as execute_js, cdp_command, or capture_page_screenshot. It implies use for reading page content, but does not state exclusions or name sibling tools. An agent must infer the appropriate context from the sibling names alone.

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