diagnose
Run the Crystalbook diagnostic against a described system. Checks the four-primitive existence equation (∃, ∂, ς, ∅) and all eight Laws, returning per-law status (SATISFIED/AT_RISK/VIOLATED), a conservation status, and prescriptions for any deviations found.
Taxonomy
Linnaean classification joined from the algovigilance taxonomy index via the parent config's rank.
| Rank | Value |
|---|---|
| domain | Substrata |
| kingdom | Constructa |
| phylum | Configa |
| class | station-config |
| order | crystalbook |
| family | mcp-tool-config |
Characteristics:
- substrate:
config - domain:
pv - lifecycle:
continuous - authority:
read - compounding:
producer - io:
agent-request→tool-response
Input schema
systemstringrequired — Description of the system, project, team, or decision to diagnose. Be specific about what exists, what its boundaries are, what state it is in, and what is missing.observationsstring — Specific observations, measurements, or evidence about the system's current state. Include any known deviations, concerns, or symptoms.
Example call
POST /api/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "station__crystalbook__diagnose",
"arguments": {
"system": ""
}
}
}How to invoke from a client
From any MCP-aware client, add https://algovigilance.com/api/mcp as an MCP server, then call this tool by name. From a raw HTTP client, send the JSON-RPC body above to /api/mcp.
Agent-friendly formats
Working inside an AI assistant? Use the Copy for AI button at the top of this page (or view the raw Markdown) to paste a clean, token-budgeted version of this tool's contract into your conversation.
Related
- All tools (3059 live)
- /api/mcp — endpoint
- /AGENTS.md — agent guide
- /tools/crystalbook__diagnose/raw.md — this page's Markdown twin