Content
78%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a tight, well-structured overview: concrete check/fix guidance with exact schema strings and properties, an explicit validation tool, and clean one-level-deep progressive disclosure into references/rule.md. Its only weaknesses are minor — a duplicated property list across two sections, a padded motivational opener, and no inline JSON-LD example in the Fix section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~40-line body is lean and assumes Claude's competence (no explanation of what JSON-LD or schema.org is), but the required-properties list ('ratingValue', 'ratingCount'/'reviewCount', 'bestRating') is repeated nearly verbatim in both 'Quick Reference' and 'Check', and the CTR-justification opener ('competitors with valid markup capture that visibility advantage') is padding that could be trimmed. This matches anchor 4 (efficient with minor instances of over-explanation) rather than 5 (every token earns its place). | 4 / 5 |
Actionability | Concrete, executable guidance throughout: exact search strings ('"@type": "Review"' / '"@type": "AggregateRating"'), exact required properties, where to nest AggregateRating ('inside the main entity (Product, LocalBusiness, etc.)'), and the named validation tool (Google's Rich Results Test). It stops short of an inline JSON-LD snippet in 'Fix' — full code lives one level deeper in references/rule.md — leaving a minor gap consistent with anchor 4 rather than the copy-paste-ready completeness of 5, and well above anchor 3 since nothing is pseudocode or missing key details. | 4 / 5 |
Workflow Clarity | A clear implied Check -> Fix -> Validate sequence with the validation tool named twice ('Validate markup with Google's Rich Results Test before deploying'). However, there is no explicit error-recovery loop (what to do when the test reports errors) and no post-deploy re-crawl step in the body itself, matching anchor 4 (clear sequence, most checkpoints present) rather than 5 (explicit validation steps with feedback loops); not 3, since validation checkpoints are explicitly present rather than missing. | 4 / 5 |
Progressive Disclosure | The body is a well-sectioned overview that defers all implementation details, code examples, and framework-specific guidance to a single clearly signaled reference ('see references/rule.md'), which exists in the bundle and is exactly one level deep with no nested references. This matches anchor 5 (clear overview with well-signaled one-level-deep references, content appropriately split). | 5 / 5 |
Total | 17 / 20 Passed |