scan_onpage_seo

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

With no annotations provided, the description carries the full burden. It discloses that the tool fetches a live URL or audits offline HTML, and mentions CLS checks for images. However, it doesn't disclose potential side effects like network requests, rate limits, or whether the tool modifies anything. Since it's a scan/audit tool, the read-only nature is implied but not explicitly stated. The description adds some behavioral context (CLS checks) but could be more transparent about fetch behavior and limitations.

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?

The description is a single, well-structured sentence that front-loads the core purpose and then lists the specific elements checked. It's concise and informative without redundancy. The only minor issue is that the list of elements is long, but it's necessary for clarity. No wasted words.

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?

The tool has no output schema, so the description should ideally hint at what the scan returns. It doesn't describe the output format or how results are structured. Given the tool's moderate complexity (multiple SEO elements checked), an agent might need to know if results are a report, scores, or raw data. The description is adequate for understanding what the tool does but incomplete for predicting the return value. Sibling tools like audit_lighthouse_cls_vitals suggest a broader audit context, but this tool's standalone completeness is moderate.

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 both parameters ('url' and 'html'). The description adds context by explaining that 'url' is for live pages and 'html' is for offline auditing, which aligns with the schema. However, it doesn't add details about parameter constraints, mutual exclusivity, or what happens if both are provided. Baseline 3 is appropriate since the schema does the heavy lifting.

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 clearly states the tool's function with a specific verb ('Scans') and resource ('On-Page SEO elements from a live URL or HTML string'), and enumerates the specific elements it checks (Meta title, Meta description, Open Graph, Twitter Cards, Canonical, Image Alt). This distinguishes it from sibling tools like audit_technical_seo or comprehensive_seo_audit, which are broader in scope.

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?

The description explicitly provides two usage modes: 'live URL' or 'HTML string', which tells an agent when to use each input. It doesn't explicitly state when not to use this tool versus siblings, but the specific focus on on-page elements implies it's for targeted on-page audits rather than broader audits. The lack of explicit exclusions or alternatives is a minor gap.

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