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

Annotations already establish read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds genuinely new context: the capture is styled, the viewport is fixed, the result is returned as a viewable image, and whole-page captures downscale enough to lose component detail. That last point is an important quality caveat not available from any structured field.

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?

Two tight sentences: the first defines the action and its output, the second delivers the scoping advice with its rationale. Nothing is padded and the actionable constraint is front-loaded in the second sentence.

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 carries the burden of describing the return value and does so ('an image you can see'), and it explains the downscaling tradeoff that affects capture choice. It is complete for a simple read-only capture tool, with only selectionOnly's relationship to targetPath left implicit.

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 the baseline is 3, and the enum values and targetPath format are already documented in the schema. The description nonetheless adds the reason to use targetPath (whole-page PNGs downscale so far that component detail becomes unreadable), which is semantic value beyond the schema. selectionOnly goes unmentioned, keeping it from a 5.

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 screenshot of the current page) plus the concrete output form (an image you can see), which is distinct from text-returning siblings like read_page. It stops short of naming the sibling tools it should be chosen over, so it is clear but not fully differentiated.

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 conditional guidance for the targetPath parameter ('when verifying ONE section'), which implicitly tells the agent when to scope vs. capture whole-page. However, it never addresses when to use swebsy_capture instead of visual alternatives such as swebsy_read_page or swebsy_read_selection, so tool-level 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.