Single tool with complete input schema and reasonable description. Naming follows verb_noun pattern (convert_html_to_pdf). Schema includes 15 parameters with types and descriptions. However, output schema is not documented, LLMs cannot predict response structure. Parameter descriptions lack actionable constraints (e.g., scale range 0.1-2 stated in description but not enforced in schema). No error handling guidance. Missing required/optional field declarations in schema.
Convert HTML file or HTML content to PDF with browser rendering. Supports CSS, JavaScript, and external resources.
Output schema not documented. Tool returns JSON with success, message, outputPath, processingTime, fileSize, but LLMs cannot predict this structure for downstream planning.
Input schema lacks 'required' field declaration. Unclear which parameters are mandatory (htmlPath vs htmlContent are mutually exclusive but not enforced).
No error handling guidance. Tool catches errors and returns isError=true with JSON message, but does not guide LLM on recovery (e.g., 'file not found, check path' or 'timeout, increase timeout parameter').
Parameter constraints stated in descriptions but not enforced in schema. Scale range (0.1-2), margin units (px, cm, in, mm), and timeout bounds should use JSON Schema minValue/maxValue/pattern.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 52 | 2026-07-28+ | v2 |
Mutually exclusive parameters (htmlPath vs htmlContent) not documented in schema. LLMs may pass both or neither, causing ambiguous failures.