Public assessment

Bigsy/Clojars-MCP-Server (clojars-deps-server)

clojars-deps-server · v0.2.0 · scanned Aug 2, 2026

What changed in the harness

Selection accuracy 98→100, token cost up 10%, unconfirmed writes 100%→100%.

Category breakdown

Where the score comes from.

Earned points across the four signals Gradable measures. Safety and Legibility are scored out of 30; Economics and Discoverability are scored out of 20.

01Safety

30.0 / 30

30.0 out of 30

02Legibility

27.6 / 30

27.6 out of 30

03Economics

20.0 / 20

20.0 out of 20

04Discoverability

16.2 / 20

16.2 out of 20

Highest-impact fix

Estimated gain +4 points

Make target tools discoverable on the first call

Clarify tool names, decision boundaries, and required argument schemas so an agent can choose and construct the target call without exploratory steps.

Description evidence

Defects and rewrites.

3 defects found across the exposed tool descriptions. Suggested rewrites make purpose, inputs, boundaries, and returns easier for an agent to understand.

Tool	Defect types	Suggested rewrite
`get_clojars_latest_version`	name_restates_behavior no_return_description	Looks up the newest published version of a Clojars/Maven dependency given as "group/artifact" (e.g. "metosin/reitit"), returning that version string.
`check_clojars_version_exists`	name_restates_behavior no_return_description	Checks whether a given version of a Clojars/Maven dependency ("group/artifact", e.g. "metosin/reitit") has been published, returning a boolean indicating existence.
`get_clojars_history`	name_restates_behavior no_return_description	Retrieves the list of published versions for a Clojars/Maven dependency ("group/artifact"), returning up to `limit` versions (default 15, max 100).

Selection evidence

Confusable tool pairs.

3 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.

Tool A	Tool B	Confidence	Why they collide
`get_clojars_latest_version`	`check_clojars_version_exists`	medium	A task like "is 0.7.2 the latest version of metosin/reitit" could plausibly be handled by either checking existence of a specific version or fetching the latest and comparing, causing selection ambiguity.
`get_clojars_latest_version`	`get_clojars_history`	low	Both return version info for a dependency, but 'latest version' vs 'history' are distinct enough intents (single value vs list) that confusion is unlikely except in vague prompts like 'what versions are available'.
`check_clojars_version_exists`	`get_clojars_history`	low	A task like "has version 1.2.0 ever been published" could be resolved by checking existence directly or scanning history, but the tools have clearly different required params (version vs limit) reducing real confusion.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard