Screenshot

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

Adds substantial context beyond readOnlyHint: Firefox ignores the BiDi clip argument, the call does not scroll by default, fullPage stitches segments inside the page and restores the original scroll position, and coordinates are physical pixels (viewport x devicePixelRatio). These are exactly the behavioral quirks an agent cannot infer from annotations or schema.

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?

Purpose is front-loaded in the first clause, then modes are ordered viewport -> fullPage -> selector, which mirrors how an agent chooses. The sentences are dense with em-dash asides but each carries a distinct behavioral fact, so little is wasted.

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?

With no output schema, the description properly states the return is base64 PNG, and it covers the main capture modes and their gotchas. The lazyLoad default behavior is only in the schema, leaving a small gap for a tool whose output is a raw payload.

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 would be 3, but the description goes further: it explains what fullPage actually does mechanically (scroll-and-stitch, scroll restore), notes that selector implies fullPage and targets a scrollable container, and clarifies the viewport default in physical pixels. Only lazyLoad goes unmentioned outside 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?

States a specific verb and resource ('Capture a base64 PNG') and describes the default scope precisely (visible viewport, physical pixels). It does not name or differentiate against siblings such as browser_pdf or browser_print, which are adjacent use cases for page capture, so it stops short of a 5.

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?

Gives clear conditional guidance: use fullPage for whole scrollable areas, use selector for a single overflow:scroll container, and notes that document scrolling alone would miss it. It does not state when NOT to use this tool or name an alternative (e.g. pdf/print for paginated output), so it is clear context without exclusions.

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