browser_vision_inspect

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial extra context: default save path and PNG format, inline WebP size/format constraints, the compacted 'unchanged' caching behavior unless force=True, and an HTTP 400 failure mode. This is unusually rich behavioral disclosure.

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 core action and its link to browser_click are front-loaded, and the rest is dense but relevant detail about output. It is somewhat run-on with heavy parenthetical asides, but every sentence carries information.

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 explains both return shapes: the element list with box_2d coordinates on a [0-1000] scale, and for inline mode data.image sizing plus css_per_image_px and per-marker image_box. An agent has what it needs to interpret results correctly.

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 only 25% (tab_id documented), so the description carries the burden and does cover the three undocumented params: inline=True behavior and image sizing, force=True for re-capture, and output_path default/returned path. It adds meaning beyond the schema, though it doesn't fully formalize each param's type/default.

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: places numbered Set-of-Mark badges on interactive elements and captures the view for visual analysis. It also names the consumer of the numbers (browser_click(mark=N)), which clearly separates it from browser_screenshot and browser_interactive_map.

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?

Usage is implied clearly ('for visual analysis', numbers feed browser_click(mark=N)) and it gives an explicit caution about not opening raw PNGs over 500 KB with an image reading tool. However, it never explicitly states when to prefer this over the sibling browser_screenshot or browser_interactive_map, so alternative-selection is left to inference.

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