Scan for AI slop

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

Adds real behavior beyond the annotations: crawling from sitemap.xml with robots.txt respected, optional local Chrome/Edge rendering, automatic before/after comparison on re-scan, and the fact that a report file is written even when the browser is not opened. It does not contradict readOnlyHint=false/destructiveHint=false, though it could say more about runtime cost and network scope for an openWorldHint tool.

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 and return shape, then a concrete usage rule. The one long sentence with the framework list is dense but earns its place by defining scan scope; overall no filler sentences.

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 8 parameters, no output schema, and no return-value documentation in the schema, the description compensates by spelling out the return payload (score, five category scores, ranked findings with evidence, fix, and file:line) and covering the folder/URL/file scoping rules. An agent has what it needs to call this correctly.

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 already 100%, but the description adds interpretation the schema lacks: which target forms count as a 'folder' (Next.js, Vite/React, Astro, Vue, Svelte, plain HTML, Markdown) and the folder-vs-URL-vs-file distinction that drives which parameters apply. That framing is genuinely additive rather than a restatement of the schema descriptions.

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 (scan) and the exact resources it accepts (URL, project folder with framework list, single .html file) plus what it detects (generic copy, cliché phrasing, placeholder leftovers, missing trust signals). The enumeration of supported project types and the description of the returned artifacts (0-100 score, five category scores, ranked findings) leave no ambiguity about what the tool does.

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?

Explicitly routes the agent: 'Prefer scanning the project folder when the user is working on the site's code; scan the URL for live sites', and open_report adds a consent condition ('Only pass true if the user agreed'). It does not, however, distinguish itself from the closely-named sibling slop_scan_html, which an agent must resolve when the input is raw HTML rather than a file path.

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