screenshot

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

With no annotations, the description carries the full load and delivers useful behavior: headless Firefox captures the page at FULL height, `width` controls the viewport, and output lands in MARIONETTE_SCREENSHOT_DIR. Missing failure/timeout/auth behavior, but the capture semantics are well disclosed.

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?

Front-loads purpose, then WHEN, then parameter/environment detail — a sensible order with no filler sentences. Slightly dense multi-clause lines, but each carries distinct 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?

An output schema exists, so return-value detail is not needed; the description still names the returned file path. For a 2-optional-param visual-capture tool it covers purpose, trigger, parameter semantics and file destination well, leaving only edge-case behavior unstated.

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 and does for both params: empty `url` captures the current page, `width` sets window width with default 1280 and 0 meaning "leave unchanged". Nothing about either parameter is left to guesswork.

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 concrete verb+resource ("PNG-скриншот страницы: вернуть путь к файлу") plus the outcome (file path), so the agent knows exactly what it produces. The "look with eyes" framing implicitly separates it from the text-fetch siblings (fetch_page, fetch_links).

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?

"КОГДА: посмотреть глазами — вёрстка, дизайн, капча" gives a clear use context (visual verification the fetch tools can't provide). No explicit when-not or named alternative, but the trigger conditions are unambiguous.

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