Content
71%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 well-structured overview that delegates depth to a single real reference file, with concrete field-level guidance and a named validation step. Its main weakness is redundancy between the Check, Fix, and Code Review sections.
Suggestions
Merge or differentiate the 'Check' and 'Code Review' sections to remove the duplicated required-field list and repeated Rich Results Test mention.
Add an explicit validation feedback loop (e.g., 'If the Rich Results Test reports errors, fix the flagged fields and re-test before treating the rule as satisfied').
Trim the 'Explain' section so it does not restate the opening paragraph's Knowledge Panel / search-results point.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and mostly lean, but the 'Check' and 'Code Review' sections are near-duplicate (both list required fields and both cite the Rich Results Test), and 'Explain' overlaps the opening paragraph. | 3 / 5 |
Actionability | The Fix section gives a concrete, complete field enumeration (@context, @type, name, PostalAddress sub-fields, telephone, url, openingHours, geo) and names a specific validation tool, though the executable code example lives in the reference file. | 4 / 5 |
Workflow Clarity | Quick Reference, Check, Fix, and Code Review form a clear audit→implement→review sequence with validation (Rich Results Test) named, but there is no explicit numbered feedback loop for error recovery. | 4 / 5 |
Progressive Disclosure | A concise (~45 line) overview with well-organized section headers and one clearly signaled, one-level-deep pointer to references/rule.md (a real file holding the code examples and framework guidance). | 5 / 5 |
Total | 16 / 20 Passed |