Loading ToolBench
A modular Model Context Protocol (MCP) server for Jira with local Ollama AI integration for ticket analysis and attachment processing
Server has 8 tools with basic schemas and descriptions, but significant gaps in parameter documentation, output schema clarity, and error handling. Tool names follow verb_noun convention (get_, summarize_, analyze_, cleanup_). Descriptions exist but are brief (10-50 chars) and lack context on when to use each tool or what they return. Parameter descriptions are minimal or absent. No visible output schema documentation. Error handling and recovery guidance are absent. Composition is reasonable (single responsibility per tool), but parameter naming lacks consistency (ticket_key vs filename). No tool annotations (readOnlyHint/destructiveHint) despite clear risk levels. Security: credentials appear to be environment-injected (good), but no audit logging visible in tool definitions.
Analyze all attachments from a Jira ticket using Ollama.
Analyze a specific attachment from a Jira ticket using Ollama.
Analyze a Jira ticket by asking a specific question about it.
Delete downloaded attachments for a specific ticket to free up disk space.
Get all tickets assigned to the current user.
Fetch and download all attachments from a Jira ticket to a local directory.
Output schemas not documented. No visible return type definitions for any tool. LLMs cannot plan downstream calls or extract required fields (e.g., ticket_id, attachment_url) without knowing response structure.
Parameter descriptions are minimal or missing. 'question' param in analyze_ticket and analyze_attachment lacks description. 'filename' in analyze_attachment has no guidance on format or constraints. LLMs cannot infer valid inputs.
Tool descriptions are too brief (10-50 chars). 'Get all tickets assigned to the current user' lacks context on pagination, filtering, or result limits. 'Summarize a Jira ticket using Ollama' does not explain when to use vs analyze_ticket. Descriptions should be 50-200 chars with selection guidance.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | <=2025-11-25 | v2 |
Get detailed information about a specific ticket.
Summarize a Jira ticket using Ollama.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Risk levels are declared (READ_ONLY, WRITE, DESTRUCTIVE) but not exposed in tool metadata. LLMs cannot reason about safety or retry semantics without annotations.
No error handling or recovery guidance visible. Tools that call external services (Jira, Ollama) lack timeout handling, partial failure modes, or actionable error messages. Agents cannot self-correct on failures.