Three tools with complete schemas and descriptions, but significant gaps in parameter clarity, error handling, and output documentation. All tools are read-only (good security posture). Schemas use Zod with descriptions, but parameter relationships are underdocumented. No output schemas documented. Error handling is minimal, API errors are passed through without recovery guidance. Tool names are clear (tickets, ticket_details, ticket_stats) but descriptions could be more concise and action-oriented.
Retrieve detailed ticket information from Axur: field values, texts/comments, detection snapshots, attachments, lifecycle transitions, takedown options, and timeline.
Retrieve Axur ticket statistics: counts by status, incidents by threat type, takedown/treatment metrics and uptime, global and market-segment incident medians/means. Note: from/to date range must not exceed 90 days.
Search, retrieve, and inspect Axur platform tickets. Actions: list (filter/search tickets), get (single ticket), bulk_get (multiple tickets by keys), history (ticket change history), types (list supported ticket types).
No output schemas documented. Tools return raw JSON via client.get() with no structure hints for LLMs. Agents cannot predict response fields or plan downstream calls.
ticket_stats: 'from' and 'to' parameters are optional but description says 'Required for most actions', undocumented conditional dependency. LLMs will omit them without explicit validation.
Error handling is absent. client.get() throws raw API errors ('Axur API error 404: ...') with no recovery guidance. LLMs receive no actionable next steps.
tickets: 'include' parameter accepts comma-separated values ('fields,snapshots,texts,attachments') but no enum constraint. LLMs may hallucinate invalid field names.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | 2026-07-28+ | v2 |
No pagination guidance in tool descriptions. tickets accepts 'page' and 'pageSize' but does not document max results, default limit, or total count in response.