01Safety
0.0 / 30
Public leaderboard
Public assessment
aashari/mcp-server-atlassian-confluence (@aashari/mcp-server-atlassian-confluence)
What changed in the harness
Selection accuracy 100%, destructive-action safety rate 0% (baseline only -- no rewrite pass applied).
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.
02Legibility
29.6 / 30
03Economics
18.8 / 20
04Discoverability
15.5 / 20
Highest-impact fix
Estimated gain +30 pointsAdd 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.
0 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 |
|---|---|---|
| No description defects were flagged in this assessment. | ||
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 |
|---|---|---|---|
conf_put |
conf_patch |
high | Both tools are described as updating Confluence resources (PUT = full replace update, PATCH = partial update), so a task like 'update this page's title' or 'change the page content' gives the agent no hint about HTTP method. conf_patch even warns that Confluence v2 primarily uses PUT for updates, actively pushing an agent toward the wrong member. |
Compare the field