Writing
Page 2 of 5
Older posts on measuring MCP servers — retries, empty results, schema cost, and what the four outcomes of a tool call actually tell you.
Page 2 of 5
-
Engineering 5 minThe Smithery registry strips required from stored schemas
Zero of 82,549 stored tools carry a top-level required array. 2,064 nested objects still carry theirs, which narrows the cause considerably.
-
Tool design 6 minThe MCP servers that get their schemas right
718 of 2,255 servers have no undescribed parameters, no colliding tools, and no unenforced closed sets. They are smaller, cheaper and more distinctive.
-
Tool design 6 minShould you split a large MCP server?
A decision framework with the corpus data as the input. Under fifteen tools the answer is no. Past sixty it is probably yes, and rewording will not save you.
-
Tool design 4 minAn MCP tool description checklist
Nine checks, each with the rate it occurs across 4,749 public servers, so you can spend your time on the two faults that are actually likely.
-
Tool design 7 minWhy the model won't call your tool
Six causes, ordered by how often they turn up in a corpus of 4,749 servers. Start with the one that is 17.7% likely, not the one that feels most plausible.
-
Tool design 6 minHow to test your MCP server's tool schemas
A twenty-minute pass — dump the real response, run four checks, fix the two faults that account for most of the corpus, then put one assertion in CI.
-
Tool design 6 minHow to read a tools/list response
The JSON your MCP server returns is the entire brief a model gets. Here is how to read it the way a model has to, field by field.
-
Measurement 4 minEight MCP servers publish no tools at all
They are listed, installable and reachable, and tools/list comes back empty. This figure was 13 until we deduplicated the corpus — a lesson in counting.
-
Tool design 5 minWhich JSON Schema features do MCP servers actually use?
default appears on 17.2% of parameters — more than enum. format is 2.1%, pattern 1.6%, and examples 0.3%. Most of JSON Schema goes unused.
-
Tool design 5 minHow deep do MCP input schemas nest?
83.1% of tools are one level deep and the deepest is thirteen. Deeply nested schemas are better documented than flat ones, not worse — 18.2% against 21.8%.
-
Tool design 5 minShould you prefix MCP tool names with the server name?
10.6% of servers do. They collide less, not more — 14.6% zero-distinctive against 18.5% — and the cost is bytes rather than clarity.
-
Tool design 5 minHow MCP authors name tools — get, list, search
Only 33.4% of 82,549 tool names start with a common verb. get alone is 15.6%, and 12,892 tools begin with it — which is where the collisions live.