완성 페이지 KWCAG 재검사

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

With no annotations, the description carries the full behavioral burden and does so unusually well: it discloses that only part of accessibility is auto-judged, that contrast is measured directly, that manual-check items are reported with their procedures, and that a pass here is not a review pass. It also reinforces that a failed interaction step invalidates the inspection and blocks the gate, which is critical operational context an agent must know before calling.

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-loaded with purpose, followed by mechanism, limitation caveat, invocation timing, and input preference — each sentence earns its place. The limitation caveat is dense (stacked em-dash clauses) but not redundant, and the whole definition stays proportionate to an 8-parameter tool.

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 tool with 8 optional parameters, no output schema, and no annotations, the description covers why, when, and with what inputs, plus the crucial 'automation is partial' caveat. What is missing is any statement of what the run returns (violations, screenshots, report layout) and how it relates to inspect_page, but with no output schema the gap is modest.

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 baseline is 3; the description adds a genuine decision rule by recommending url (dev server/deploy) or filePath (local HTML) and explaining that relative-path assets resolve correctly in those modes. This prioritization goes slightly beyond the per-field schema text, though most parameter detail is still schema-supplied rather than description-supplied.

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 gives a specific verb+resource+standard: re-inspects an assembled/converted page in a real browser against KWCAG 2.2, running axe-core and translating results into the 33 KWCAG items. It also clarifies scope beyond automation ('passing here does not mean passing review'), which separates it from a generic inspection. It never names the closest sibling (inspect_page), so an agent must infer the boundary rather than being told.

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?

Explicit invocation timing is given as a workflow sequence: call after converting templates to a framework, after assembling the page, and after filling content. It also steers input choice (url or filePath recommended, html as last resort) and warns against mutating initial values via temporary builds. No alternative sibling tool is named and no clear exclude case is stated, so it stops short of a 5.

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