Server has 10 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have descriptions (10-50 chars, below ideal 50-200 char baseline) and Zod-based input schemas. However, descriptions are generic and lack actionable context. No output schemas documented. Error handling returns raw error messages without recovery guidance. No tool annotations (readOnlyHint/destructiveHint). Parameter descriptions exist but lack format constraints, ranges, or enum values. Tools mix Jira and Confluence concerns without clear separation. No pagination support despite search tools returning potentially large result sets.
Add a comment to a Jira issue
Create a new Jira issue
Create a new Confluence page
Retrieve a Jira issue by its key
Retrieve a Confluence page by its ID
Get all pages in a Confluence space
Search for Jira issues using JQL query
Descriptions are too short (10-50 chars vs. baseline 50-200 chars). Generic descriptions like 'Retrieve a Jira issue by its key' lack context for when/why to use the tool. LLMs cannot distinguish between similar tools (get_issue vs search_issues) without richer guidance.
No output schemas documented. Callers cannot predict response structure. create_issue returns 'Issue created successfully. Key: {key}' as plain text; LLMs cannot extract the key for downstream tool calls without parsing unstructured text.
Error handling returns raw error messages without recovery guidance. 'Error fetching issue: {error.message}' tells LLM nothing about whether to retry, ask user, or abandon. No error classification (retryable vs. fatal).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 48 | 2026-07-28+ | v2 |
Search for Confluence pages
Update an existing Jira issue
Update an existing Confluence page
No pagination support. search_issues and search_pages accept maxResults but return all results in one response. Large result sets (100+ issues) blow context window. No next_cursor or offset mechanism documented.
No tool annotations. Destructive tools (create_issue, update_issue, delete operations) lack destructiveHint. Read-only tools lack readOnlyHint. LLMs cannot distinguish safe from risky operations without explicit hints.