Loading ToolBench
Server defines 4 tools with partial schemas and descriptions. All tools have descriptions (10-200 chars), but parameter documentation is incomplete. create_diff and open_file have well-structured input schemas with type definitions and descriptions. However, open_project and check_extension_status lack detailed parameter descriptions. No output schemas are documented. Error handling is minimal, tools do not guide recovery or categorize errors. Tool names follow verb_noun convention (create_diff, open_file, open_project, check_extension_status), which is good, but descriptions lack WHEN/WHY context that LLMs need for tool selection. No tool annotations (readOnlyHint, destructiveHint) despite create_diff being a write operation. Composition is reasonable, each tool has one responsibility, but no pagination, batch operations, or idempotency guarantees documented.
Check if the VS Code MCP Extension is installed and responding
Use this instead of writing files directly. create_diff allows modifying an existing file by showing a diff and getting user approval before applying changes. Only use this tool on existing files. If a new file needs to be created, do not use this tool.
Used to open a file in the VS Code editor. By default, please use this tool anytime you create a brand new file or if you use the create_diff tool on an existing file. We want to see changed and newly created files in the editor.
Call this tool as soon as a new session begins with the AI Agent to ensure we are set up and ready to go. open_project opens a project folder in VS Code. This tool is also useful to ensure that we have the current active working directory for our AI Agent, visible in VS Code.
No output schemas documented. LLMs cannot plan downstream calls or extract required fields. create_diff, open_file, open_project, and check_extension_status all lack response structure definitions.
create_diff is a destructive write operation but lacks tool annotations (destructiveHint). Agents cannot distinguish safe reads from irreversible writes without explicit hints.
Parameter descriptions are generic or missing. 'targetProjectPath' appears in 3 tools but is never explained. 'viewColumn' in open_file lacks guidance on valid range (1, 2, 3, etc.). LLMs cannot infer constraints from names alone.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | <=2025-11-25 | v2 |
No error handling guidance. Tools do not return actionable error messages or recovery hints. If create_diff fails (file not found, permission denied), the agent has no guidance on next steps.
Tool descriptions lack WHEN/WHY context. 'Call this tool as soon as a new session begins' (open_project) is procedural but does not explain what the tool returns or why an agent should call it. Descriptions should answer: What does it do? When to use it? What does it return?