A sticky notes MCP server that allows appending, reading, and summarizing notes with AI assistance
Two tools with minimal documentation. add_note has a basic description (67 chars) but lacks parameter description detail; read_notes has a typo-ridden description (95 chars, 'lie' instead of 'line', 'axist' instead of 'exist') and no parameters to describe. Both tools have input schemas visible in FastMCP decorators, but descriptions fall short of production standards (baseline 194 chars). No error handling guidance, no output schema documentation, no parameter constraints or validation hints. Naming is acceptable (verb_noun pattern), but overall quality is well below A/B grade standards.
append a new note to sticky notes args: message(str): the note content to be added returns: confirming message indicating the note was saved
read and return all notes from the sticky not file returns str: all notes as single string seprated by the lie if no notes axist a default message is returned
read_notes description contains typos ('lie' for 'line', 'axist' for 'exist') and lacks clarity on return format and error cases
add_note parameter 'message' lacks description in schema; LLM cannot infer constraints, format, or length limits
No output schema documented for either tool; LLMs cannot plan downstream calls or validate responses
No error handling or recovery guidance; tools fail silently or return generic messages without actionable next steps
Tool descriptions are below baseline length (194 chars); add_note at 67 chars, read_notes at 95 chars lack context for LLM selection
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 42 | 2026-07-28+ | v2 |