# Microgram: perturbation-novelty-assessor

`station__algovigilance__microgram-perturbation-novelty-assessor` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Evaluates whether a safety analysis approach uses the three architectural innovations that distinguish the perturbation pattern framework from existing QSP/AOP/network pharmacology. Exercises κ (Comparison) — measures distance from conventional endpoint-specific modeling.

## Agent metadata

- `idempotent`: true
- `read_only`: true
- `expected_latency_ms`: unknown (not yet contract-tested)
- `cost_tokens_estimate`: unknown

## Input schema

- `representation_decoupled` *boolean* (required) — Input variable representation_decoupled
- `representation_learned` *boolean* (required) — Input variable representation_learned
- `boundary_parameterized` *boolean* (required) — Input variable boundary_parameterized
- `num_boundaries_evaluated` *number* — Input variable num_boundaries_evaluated
- `has_novel_boundary` *boolean* — Input variable has_novel_boundary
- `baseline_approach` *string* — Input variable baseline_approach

## Example call

```json
POST /api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-perturbation-novelty-assessor",
    "arguments": {
      "representation_decoupled": false,
      "representation_learned": false,
      "boundary_parameterized": false
    }
  }
}
```

## Related

- [/tools](/tools) — all 7718 tools
- [/tools/algovigilance__microgram-perturbation-novelty-assessor](/tools/algovigilance__microgram-perturbation-novelty-assessor) — HTML page
- [/tools/algovigilance__microgram-perturbation-novelty-assessor/json](/tools/algovigilance__microgram-perturbation-novelty-assessor/json) — JSON form (agent-friendly)
- [/api/mcp](/api/mcp) — endpoint
- [/AGENTS.md](/AGENTS.md) — agent guide