Open-source, self-hostable documentation platform that provides AI-friendly documentation parsing and publishing capabilities
Shiru exposes 8 tools with severe definition gaps. Most tools lack visible input schemas in the provided source code. Tool names use inconsistent patterns (healthCheck vs docs.publish vs onboarding.*). Descriptions are present but generic and lack actionable context. No parameter descriptions visible. No output schemas documented. Error handling and recovery guidance absent. Overall, this server falls well below production quality baselines.
Get documentation site settings including active commit SHA and site ID
Fetch latest docs from GitHub and publish them instantly
GitHub integration procedures
Health check endpoint that returns OK status
Onboarding workflow procedures
Organization management procedures
User management procedures
Add an email address to the waitlist
No input schemas visible for 6 of 8 tools. healthCheck, onboarding.*, organization.*, user.*, and github.* lack documented parameter schemas.
Wildcard tool names (onboarding.*, organization.*, user.*, github.*) are inferred, not explicitly registered. These lack specificity, LLMs cannot determine which sub-operation to invoke.
Descriptions are generic and lack actionable context. 'Onboarding workflow procedures' does not explain WHAT the tool does, WHEN to use it, or what it returns.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 38 | 2026-07-28+ | v2 |
No parameter descriptions visible. Even docs.publish's docsSiteId lacks explanation of what a 'site ID' is, how to obtain it, or valid format. LLMs cannot infer parameter meaning from names alone.
No output schemas documented. Callers cannot know what fields to expect from responses, breaking downstream tool chaining and forcing LLMs to guess at response structure.