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

Adds context beyond annotations: the call consumes plan credits/limits, long captures return asynchronously and must be polled, and retries must reuse the same key. That retry note sits alongside idempotentHint=false (idempotency is only guaranteed by supplying the key), which is complementary rather than contradictory. Not stated: whether reusing a key returns the original result or errors.

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?

Five short sentences, front-loaded with what it does, then cost, then async, then retry semantics. Efficient, though "Accepts the existing screenshot options" is a low-value sentence that spends space without informing.

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?

For a high-complexity, heavily nested tool with no output schema and no per-parameter documentation, the description covers operational concerns (cost, async, idempotency) but leaves the large options object, output selection, and the shape of the response entirely unaddressed.

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% and the options object nests ~30 undescribed fields (actions, outputs, session, blockLevel, fullPageMode, etc.). "Accepts the existing screenshot options" defers to documentation the agent may not have; only async and idempotencyKey get any treatment, leaving the bulk of the surface unexplained.

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?

"Capture a website" gives a verb and resource but is close to restating the tool name, and it never states that this captures a single URL (versus capture_screenshots_bulk) or that the capture can yield screenshot/PDF/HTML/Markdown/JSON outputs. An agent cannot tell from the description alone what the primary artifact is.

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?

It gives concrete operational routing: use async=true for long captures, then poll get_screenshot, and reuse idempotencyKey on retries. It does not address when to choose capture_screenshots_bulk or get_screenshot_result instead, so it stops short of full alternative coverage.

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