API Docs Generator

Write Markdown API documentation from an OpenAPI spec or a description, with parameters, examples and error codes.

Pay by wallet (x402) AI-generated api-docs-generate

Example

Input
{
  "endpoint_description": "This is a test input for automated capability testing."
}
Answer
{
  "markdown": "# API Documentation\n\n## Description\n\nThis is a test input for automated capability testing.\n\n## Authentication\n\nNo authentication is currently configured for this API.\n\n## Endpoints\n\nNo endpoints have been specified in the provided specification.\n\n## Parameters\n\nNo parameters are defined.\n\n## Request Example\n\n```\nNo examples available\n```\n\n## Response Example\n\n```\nNo examples available\n```\n\n## Error Codes\n\nNo error codes are documented.",
  "source_type": "natural_language",
  "total_endpoints": 0,
  "authentication_type": "none",
  "endpoints_documented": []
}

Inputs

FieldTypeRequiredWhat it is
openapi_specstringNo—
endpoint_descriptionstringNo—

Output fields

How reliably each field appears in a successful answer.

FieldTypeAppears
markdownstringAlways (present in every successful answer)
total_endpointsintegerAlways (present in every successful answer)
endpoints_documentedarrayAlways (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "api-docs-generate",
    "inputs": {
      "endpoint_description": "This is a test input for automated capability testing."
    },
    "max_price_cents": 20
  }'

Limitations

  • Undocumented API behaviour is not inferred

    Generated documentation reflects the provided API spec — undocumented behaviour and edge cases are not inferred

    What to do instead: Review generated docs against actual API behaviour and add examples for complex endpoints

  • Output size cap per call

    Structured output is limited to about 2000 output tokens per call; requests exceeding this limit are refused rather than returned truncated. Requests with large results can exceed this limit, and repeating the same request does not help.

    What to do instead: Provide a smaller spec or split it into fewer endpoints per call

Bundled checks that include it