An MCP server for managing sticky notes with add, read, and summarization capabilities
This server has critical gaps in definition quality. Tool descriptions are present but minimal (10-50 chars, well below the 194-char baseline). Parameters lack descriptions entirely, the 'message' param in add_note has no guidance on format, length, or constraints. No output schemas are documented; tools return bare strings without structure. The prompt_for_note tool is misclassified as a tool when it should be a prompt resource. Error handling is absent, no guidance on what to do if file I/O fails. No input validation, no pagination support, and no security considerations for file path handling.
Append a new note to the sticky note file.
Get the path to the notes file.
Prompt the user to summarize the notes.
Read all notes from the sticky note file.
Parameters lack descriptions. 'message' in add_note has no guidance on format, length, or constraints. LLMs cannot infer valid input ranges.
No output schemas documented. Tools return bare strings (e.g., 'Note added successfully!') without structured fields. Agents cannot extract or chain results.
Tool descriptions are too short (10-50 chars vs. 194-char baseline). 'Append a new note to the sticky note file' lacks context on when to use it vs. other tools, prerequisites, or side effects.
No error handling or recovery guidance. If file I/O fails, tools return nothing. LLM has no guidance on retry, fallback, or user notification.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
prompt_for_note is registered as a tool but should be a prompt resource. Prompts are not tools, they do not accept input or return structured output. Misclassification confuses the agent.