Personal-use MCP server for Claude Desktop providing professional-grade stock analysis and technical indicators
Scoring was not performed
Tool names do not follow action-verb conventions. 'tool_name' and 'public_tool_name' are generic placeholders that do not convey what action is performed. LLMs cannot infer intent from the name alone.
Descriptions are below the 20-character minimum for actionable LLM guidance. 'Brief description of what this tool does' (tool_name) and 'A public tool that doesn't require authentication' (public_tool_name) lack context on WHEN to use these tools, WHAT they return, and HOW they differ from each other.
No output schemas documented. It is unknown what fields these tools return, making it impossible for downstream tools to chain results or for LLMs to extract needed data.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 38 | 2026-07-28+ | v2 |
| 2026-03-09 | F | 19 | - | v1 |
Parameter 'param1' and 'param2' in tool_name lack clear purpose descriptions. 'Description of first parameter' is a placeholder, not an actual explanation. LLMs cannot determine valid values or constraints.
No error handling documentation. Tools do not describe what happens on failure, recovery paths, or how the LLM should react to errors.
Tool definitions appear to be templates or placeholders. File references point to 'tools/templates/new_tool_template.py', this suggests the tools are not real implementations but example stubs.