Public leaderboard

Public assessment

jawdat6/fixgraph-mcp (fixgraph-mcp)

fixgraph-mcp · v1.0.3 · scanned

What changed in the harness

Selection accuracy 100→100, token cost up 5%, unconfirmed writes 0%→0%.

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

0.0 / 30

0.0 out of 30
02Legibility

29.0 / 30

29.0 out of 30
03Economics

20.0 / 20

20.0 out of 20
04Discoverability

11.0 / 20

11.0 out of 20

Highest-impact fix

Estimated gain +30 points

Add explicit identity and permission preflight tools

Expose machine-readable principal/tenant confirmation and a non-mutating permission check so agents can verify both before destructive actions.

Description evidence

Defects and rewrites.

2 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
fixgraph_get_fixes
no_return_description
Fetches a FixGraph issue by its ID or slug (from a fixgraph_search result) and returns all verified fixes associated with it, including their details and how to apply them.
fixgraph_submit_fix
name_restates_behavior no_return_description
Creates a new fix attached to an existing FixGraph issue, supplying its title, root cause, ordered fix steps, validation method, and risk level. Requires the FIXGRAPH_API_KEY environment variable. Returns the outcome of the submission so callers can confirm the fix was recorded.

Selection evidence

Confusable tool pairs.

1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.

Tool A Tool B Confidence Why they collide
fixgraph_search fixgraph_get_fixes medium Both tools present as read-only 'fix lookup' operations and both descriptions prominently mention 'fixes'. A user task like 'get the fixes for issue abc-123' could route to fixgraph_search because its description says 'Search FixGraph for engineering fixes' and it is the more general look-up tool, even though the correct choice (fixed issue_id input) is fixgraph_get_fixes. Since fixgraph_search never accepts an issue_id and only returns issues (not fixes), an agent paraphrasing 'get fixes' may pick the wrong one unless it notices the issue_id semantics.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard