A Model Context Protocol server for Bitbucket integration
Server has 10 tools with complete input schemas and basic descriptions. All tools follow verb_noun naming (get_, list_, create_, update_, merge_, decline_). Schemas are properly typed with required fields. However, descriptions are generic (avg ~50 chars, well below the 194-char baseline for A+ tools) and lack context about when to use each tool, prerequisites, or recovery guidance. Parameter descriptions are minimal. No output schemas documented. Error handling is absent from visible code. Tool descriptions do not indicate state-modifying consequences (WRITE/IRREVERSIBLE risks). Missing pagination guidance for list tools.
Create a new pull request
Create a new repository
Decline a pull request
Get detailed information about a specific pull request
Get detailed information about a specific repository
List pull requests for a repository
List all repositories in a workspace
Descriptions are generic and lack LLM-optimized context. Average ~50 chars vs. 194-char baseline. No guidance on when to use each tool, prerequisites, or how results chain to downstream tools.
No output schemas documented. LLMs cannot infer what fields are returned or plan downstream tool calls. Violates pattern:tool requirement.
State-modifying tools (create_*, update_*, merge_*, decline_*) do not document their irreversible consequences in descriptions. LLMs cannot distinguish safe retries from destructive operations.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
Merge a pull request
Search code in a repository
Update a pull request's title or description
List tools (list_repositories, list_pull_requests) lack pagination parameters (limit, offset/cursor) and no result-count guidance. Large result sets will blow context windows.
No error handling or recovery guidance visible in tool definitions. Errors will not guide LLMs on retry strategy, user-fixable issues, or next steps.