Two tools with basic schemas and descriptions, but significant gaps in parameter documentation, output schema clarity, and error handling guidance. get_issues lacks parameter constraints and output schema documentation. create_issue has 5 parameters but no enum constraints, format specifications, or validation rules. Neither tool documents what fields are returned or how to chain results. Error responses are generic text blobs rather than structured guidance. No pagination support despite API returning up to 100 items. Descriptions are adequate (50-60 chars) but lack WHEN/WHY context. No tool annotations (readOnlyHint/destructiveHint) despite clear risk differences.

• Add explicit output schema documentation for both tools. For get_issues, document that it returns {issues: [{idReadable, summary, project.name, created, updated}]}. For create_issue, return {success: boolean, issue_id?: string, error?: string}.
• Add format and range constraints to create_issue parameters: dueDate as ISO 8601 string (YYYY-MM-DD), estimation as number 1-480 (minutes, max 8 hours). Document in parameter descriptions.
• Enhance error responses with recovery guidance. E.g., 'User "john" not found. Try calling get_issues with a different username or search_users() if available.'
• Add tool annotations: mark create_issue with destructiveHint=true; mark get_issues with readOnlyHint=true. This signals agent safety constraints.
• Add pagination to get_issues: accept optional limit (1-100, default 20) and offset parameters; return {issues: [...], total_count: N, has_more: boolean}.