Loading ToolBench
Convert HTML to clean Markdown -- strips scripts/styles, preserves headings, links, lists, images.
Single tool with adequate naming and schema, but description is verbose and contains anti-patterns (example values, references to non-existent tools). Input schema is properly typed. Output structure documented in description text rather than formal schema. Tool description exceeds 1024 char baseline and includes example JSON output, which LLMs may reuse literally. No parameter descriptions beyond the HTML input field. Error handling and recovery guidance absent.
Use this when you need to convert HTML to clean Markdown text. Returns the converted markdown in JSON. Returns: 1. markdown (converted text) 2. inputLength (character count of HTML) 3. outputLength (character count of markdown) 4. strippedElements (scripts, styles, iframes removed). Example output: {"markdown":"# Hello World\n\nThis is **bold** and *italic*.\n\n[Link](https://example.com)","inputLength":156,"outputLength":68,"strippedElements":["script","style"]} Use this FOR converting web content to LLM-friendly format, migrating CMS content, cleaning up HTML emails, and preparing content for markdown-based systems. Do NOT use for markdown to HTML -- use text_convert_markdown_to_html instead. Do NOT use for web scraping (fetching + converting) -- use web_scrape_to_markdown instead. Do NOT use for PDF generation -- use document_generate_pdf instead.
Description contains example output JSON and references to non-existent tools ('text_convert_markdown_to_html', 'web_scrape_to_markdown', 'document_generate_pdf'). LLMs may hallucinate these tools or reuse example values literally in real calls.
Output schema not formally documented in JSON Schema format. Structure (markdown, inputLength, outputLength, strippedElements) is described in prose only. LLMs cannot reliably parse unstructured descriptions to plan downstream operations.
No error handling guidance. Tool description does not explain what happens on invalid HTML, encoding errors, or oversized inputs. LLMs have no recovery path if the tool fails.
Single parameter 'html' lacks description. While the name is clear, a formal description explaining expected encoding, size limits, and valid HTML variants would improve LLM reliability.
Inferred effective spec: 2025-06-18+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 60 | 2025-06-18+ | v2 |
Description exceeds 1024 character baseline (approximately 1200+ chars). Verbose descriptions waste tokens and bury key details. Condense to 150-250 chars with formal output schema.