Convert any ArXiv research paper to clean structured Markdown. Accepts both abstract page URLs (arxiv.org/abs/PAPER_ID) and direct PDF links (arxiv.org/pdf/PAPER_ID). Returns the full paper content with headings, sections, and content preserved — uses significantly fewer tokens than the PDF format for AI analysis.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the output format, preservation of headings/sections, and the token efficiency benefit, which is meaningful behavioral detail. It could mention limitations like paywalled content, but the core behavior is well covered.
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 three focused sentences with no redundant phrasing. Each sentence adds value: what it does, supported inputs, and output/token benefit.
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?
For a single-parameter conversion tool, the description is complete: it covers the input type, output format, and use case. The presence of an output schema further reduces the need to describe return values in detail.
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 coverage is 0% for the single 'url' parameter, but the description fully compensates by detailing both accepted URL patterns (arxiv.org/abs/PAPER_ID and arxiv.org/pdf/PAPER_ID). This is exactly the semantic guidance needed beyond the bare property name.
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 converts ArXiv research papers to structured Markdown, using a specific verb and resource. It distinguishes itself from sibling conversion tools by explicitly targeting ArXiv URLs.
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 lists the accepted URL formats (abstract pages and PDF links), which tells the agent exactly when this tool is appropriate. It does not explicitly exclude other cases, but the ArXiv focus provides clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools overlap: convert_url already supports ArXiv and YouTube, making convert_arxiv and convert_youtube redundant. convert_with_metadata duplicates convert_file/convert_url but adds a metadata header. Agents must read descriptions carefully to choose correctly.
All tool names follow a consistent snake_case verb_noun pattern: convert_*, count_tokens, list_supported_formats, prepare_for_rag. No mixed conventions or vague verbs exist.
9 tools is well-scoped for a document conversion service. Each tool has a distinct role (file, URL, batch, metadata, token counting, format listing, RAG preparation) without being bloated.
The domain of converting sources to Markdown is thoroughly covered: files, URLs, batch conversion, metadata, token counting, and RAG chunking. The only minor redundancy is the specialized source converters, but the core workflow is complete.
