Reference MCP tools for NetBox lab topology and reservation workflows (mock backend)
Server has 7 tools with basic schemas and descriptions, but significant gaps limit production readiness. Tool descriptions are present but minimal (10-50 chars, well below the 194-char baseline). Parameter descriptions are sparse or missing entirely. No output schemas documented. Error handling is minimal. Most parameters lack type constraints (enums, ranges). The server exposes a mock backend suitable for reference/testing but lacks production-grade polish.
Check reservation conflicts (mock always returns zero).
Create a reservation for a topology.
Create a draft lab topology in the mock NetBox store.
Get a topology with nodes and links.
List all topologies in the mock store.
Release a topology back to draft.
Mark a topology as resolved.
Parameter descriptions missing or trivial. 'name', 'site', 'slug', 'description', 'topology_id', 'start', 'end', 'owner_username' have no descriptions in the schema. LLMs cannot infer parameter meaning from names alone.
Tool descriptions are too short (10-50 chars vs. 194-char baseline). 'Get a topology with nodes and links' lacks context on when to use it vs. list_topologies, what fields are returned, or prerequisites.
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields (e.g., topology_id returned by create_topology). Responses are unstructured.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
No enum constraints on string parameters. 'site' and 'slug' accept free-form strings; no validation guidance. 'start' and 'end' accept ISO-8601 but lack format specification in schema.
Error handling minimal. Tools return dict responses but no guidance on error classification (retryable vs. fatal) or recovery steps. 'VALIDATION_ERROR' in create_reservation_tool is not exposed in the MCP tool definition.