Public leaderboard

Public assessment

muhannad-hash/git-context-mcp (git-context-mcp)

git-context-mcp · v1.1.0 · scanned

What changed in the harness

Selection accuracy 100→100, token cost up 2%, 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

29.4 / 30

29.4 out of 30
03Economics

20.0 / 20

20.0 out of 20
04Discoverability

18.6 / 20

18.6 out of 20

Highest-impact fix

Estimated gain +1 point

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.

1 defect 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
file_contributors
no_return_description
Returns the full list of every author who has ever committed to a file, ranked by number of commits. For each author it provides their commit percentage of the file's history, current line ownership, and the active date range during which they committed to the file, enabling identification of the file's primary maintainers and when they were active.

Selection evidence

Confusable tool pairs.

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

Tool A Tool B Confidence Why they collide
commit_story search_commits low Definitions cleanly split a hash-keyed lookup vs a keyword search, so most tasks map unambiguously. Confusion is only plausible for a task like 'tell me the full story/details of the commit that fixed X', where the agent has no hash and might call commit_story directly instead of search_commits; genuine wrong-pick risk is low.
file_history file_contributors medium Both take the same file-path input and concern commits touching a file, so a task phrased such as 'who has committed to this file' or 'who has been working on this file' could plausibly route to the wrong one: history returns the recent commits, contributors returns the ranked authors. The line between 'commits on this file' and 'people on this file' is thin in natural language.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard