I graded 36 popular MCP servers on agent usability. A third got a D or F

> well-documented big catalogs are possible; they're just rare

They’re not that rare, it’s just that flat big catalogs don’t work well.

The most common failure mode for MCP server design is mapping MCP tools to system APIs. This results in a tool to list files, a tool to rename a file, a tool to copy a file, etc.

You can have 100 “tools”, you just need to define 10-12 areas (actual tools in the MCP model) and actions within each one. It creates a hierarchy that models can dive into when needed and avoid context clutter when that area is not needed.

So instead of 15 tools for file operations you have a single “file” tool, with actions like list, copy, rename, etc.

Single biggest arch requirement for any MCP server (well, any that has more than a handful of operations).

JSON and CSV [and a massive amount of custom-made spaghetti code] gave the impression that semantics was totally unnecessary in dataflows. Now that we live in a world where dataflows build themselves, we will need a description language that is much more robust. Probably generated from chatbot interactions, but formally defining how the consumer can discover content and mix them.

Be warned, AI Slop ahead

Somewhat ironically the link to your results table is broken