Model Context Protocol (MCP) server for X Y Z
Single tool with critical definition gaps. Tool name 'get_random_image' follows verb_noun convention (+), but input schema is completely empty object {} with no parameters documented. Description is present (47 chars) but minimal and lacks context on when/why to use it. No output schema documented. No error handling guidance. No parameter descriptions (N/A due to empty schema). Tool does not accept user input, limiting composability.
Get a random image using the Lorem Picsum API
Input schema is empty object {}, no parameters defined or documented.
No output schema documented. LLMs cannot plan downstream operations or extract image metadata. Tool returns image block but no documentation of response structure.
Description is 47 characters, below baseline (194 chars avg). Lacks WHAT (returns random image), WHEN (use case), and any prerequisites. Does not explain that tool fetches from external API or handles errors.
No error handling guidance. Code throws 'Failed to fetch image: {statusText}' but LLM receives no recovery path. What should agent do if API is down? Retry? Fallback?
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 34 | 2026-07-28+ | v2 |
Tool accepts no parameters, limiting composability. Cannot specify image size, format, or seed. Agents cannot customize behavior, every call returns identical random image.