페이지 시각 상태 점검

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

With no annotations, the description carries the full disclosure burden. It does well on what gets read (computed styles and font-application/fallback detection) but says nothing about the cost of rendering a browser page, what happens when a selector matches nothing, or how the results come back.

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?

Three sentences, front-loaded with what is read, then the usage triggers, then the required inputs. The property enumeration is long but informative rather than wasteful; nothing reads as filler.

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?

There is no output schema, so the description partially compensates by listing the style properties it returns. Gaps remain around non-matching selectors, the 20-selector cap, and rendering/time cost, but for a read-only inspection tool this is close to sufficient.

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 100%, so the schema already documents url, html, filePath and selectors, making 3 the baseline. The description restates 'url or filePath plus a selector list' but omits the html fallback parameter entirely, so it adds little beyond 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?

The description names a specific verb-and-resource pair: it reads computed styles (color, background, font, size, layout, margin, padding, gap) and font-application status from a rendered page. That is precise enough to separate it from get_tokens (token values) and validate_page (assertions), though it never names a sibling explicitly.

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 triggering questions ('what color is this element', 'is the font really applied or a system fallback', 'where is it positioned') and an anti-pattern (don't spin up a temporary playwright script). It stops short of an explicit when-not-to-use or a named alternative tool.

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