Loading ToolBench
Simple MCP server for Claude Code one-shot execution
Single tool 'claude_code' has a lengthy description (500+ chars) but lacks critical structure. Input schema is present with two parameters (prompt, workFolder), both with descriptions. However, the schema is minimal, no type constraints, enums, or validation rules. The description reads as marketing copy rather than LLM-optimized guidance. No output schema is documented. The tool performs multiple unrelated operations (file ops, git, terminal, web search) in one call, violating single-responsibility principle. Risk is marked IRREVERSIBLE but no confirmation/dry-run pattern is offered. Parameter descriptions lack format/constraint details (e.g., workFolder must be absolute path, but this is buried in prose, not in schema constraints).
Claude Code Agent: Your versatile multi-modal assistant for code, file, Git, and terminal operations via Claude CLI. Use `workFolder` for contextual execution. • File ops: Create, read, (fuzzy) edit, move, copy, delete, list files, analyze/ocr images, file content analysis └─ e.g., "Create /tmp/log.txt with 'system boot'", "Edit main.py to replace 'debug_mode = True' with 'debug_mode = False'", "List files in /src", "Move a specific section somewhere else" • Code: Generate / analyse / refactor / fix └─ e.g. "Generate Python to parse CSV→JSON", "Find bugs in my_script.py" • Git: Stage ▸ commit ▸ push ▸ tag (any workflow) └─ "Commit '/workspace/src/main.java' with 'feat: user auth' to develop." • Terminal: Run any CLI cmd or open URLs └─ "npm run build", "Open https://developer.mozilla.org" • Web search + summarise content on-the-fly • Multi-step workflows (Version bumps, changelog updates, release tagging, etc.) • GitHub integration Create PRs, check CI status • Confused or stuck on an issue? Ask Claude Code for a second opinion, it might surprise you! **Prompt tips** 1. Be concise, explicit & step-by-step for complex tasks. No need for niceties, this is a tool to get things done. 2. For multi-line text, write it to a temporary file in the project root, use that file, then delete it. 3. If you get a timeout, split the task into smaller steps. 4. **Seeking a second opinion/analysis**: If you're stuck or want advice, you can ask `claude_code` to analyze a problem and suggest solutions. Clearly state in your prompt that you are looking for analysis only and no actual file modifications should be made. 5. If workFolder is set to the project path, there is no need to repeat that path in the prompt and you can use relative paths for files. 6. Claude Code is really good at complex multi-step file operations and refactorings and faster than your native edit features. 7. Combine file operations, README updates, and Git commands in a sequence. 8. Claude can do much more, just ask it!
Tool performs multiple unrelated operations (file ops, git, terminal, web search, GitHub) in a single call. Violates single-responsibility principle. Should be split into separate tools (create_file, run_git_command, run_terminal, search_web, create_pr) so agents can compose them independently.
No output schema documented. LLMs cannot predict what fields to expect from the response, making downstream tool chaining impossible and forcing agents to parse unstructured output.
Description is 500+ characters of marketing copy ('Confused or stuck? Ask Claude Code for a second opinion'). Exceeds 200-char baseline for LLM-optimized descriptions. Lacks clear WHAT/WHEN/WHY structure. Does not state that this tool is irreversible and may modify files, run arbitrary commands, or push to git.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 42 | 2026-07-28+ | v2 |
Parameter 'workFolder' description states 'Mandatory when using file operations' but schema does not mark it as conditionally required. No enum, pattern, or format constraint in schema. Constraint is buried in prose, not machine-parseable.
Tool marked IRREVERSIBLE (deletes files, pushes git, runs arbitrary commands) but offers no dry-run, confirmation, or undo mechanism. Agents can cause catastrophic data loss without safeguards.