markdown_to_htmlRender Markdown (GitHub-flavored: tables, fenced code, task lists) to clean HTML with raw inline HTML stripped. POST { markdown } (max 500KB). Price: $0.003/call with credits key; free demo without (2KB input cap).
| Name | Required | Description | Default |
|---|---|---|---|
| markdown | Yes | GitHub-flavored Markdown, max 500KB |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that raw inline HTML is stripped (a security/behavioral trait), specifies input size limits (500KB, 2KB demo), and mentions pricing/authentication (credits key). It does not describe the output format or error behavior, but the key behavioral traits an agent needs are 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 extremely concise: two sentences with no fluff. It front-loads the primary action and packs in necessary details (GFM features, stripping, limits, pricing) without redundancy. Every sentence earns its place.
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 with no output schema, the description is sufficiently complete. It covers input constraints, processing details, and cost/access. While it doesn't explicitly state the return format, 'to clean HTML' implies the output. Given the simplicity, it lacks only error-handling details, but overall it is adequate.
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?
The schema already documents the 'markdown' parameter with its type and max size, so the baseline is 3. The description adds value by stating the HTTP method (POST), repeating the 500KB limit, and introducing the demo 2KB cap—an extra constraint not in the schema. This provides additional semantic clarity beyond the schema.
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's function: rendering Markdown to clean HTML, with specific mention of GitHub-flavored elements (tables, fenced code, task lists). It distinguishes from sibling tools like html_to_markdown by its direction, and the title 'Markdown → HTML' reinforces the purpose.
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 provides clear context on when to use the tool (converting Markdown to HTML, specifically GitHub-flavored) and notes important constraints (max 500KB, stripping inline HTML, demo vs paid tiers). It does not explicitly mention alternatives or exclusions, but the main use case is evident from the description despite not naming sibling tools.
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.
Each tool has a unique, non-overlapping purpose. Even closely related tools like html_to_markdown and markdown_to_html are clearly inverses, and read_page combines fetching and conversion, so no two tools could be confused for the same task.
All names are lowercase with underscores, maintaining a consistent syntactic style. However, there is no strict verb-noun pattern: some names are nouns (cron, diff, qr, timezone), others are verbs (convert, extract), and word order varies (email_verify vs validate_ids), which is a minor deviation.
With 13 tools, the count is well within the ideal 3-15 range. Each tool provides a distinct paid utility, and none feel redundant or out of place for a general-purpose vending machine API.
The tool surface covers a broad range of common utilities—format conversion, validation, extraction, formatting, and time handling. There are minor gaps like missing YAML conversion or raw HTML fetching, but these are not critical for the server's stated purpose as a collection of paid utilities.