01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→95, token cost up 1%, 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.
02Legibility
29.3 / 30
03Economics
20.0 / 20
04Discoverability
10.9 / 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.
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 |
|---|---|---|
update_status |
params_unexplained no_return_description |
Update a comment's status. The id is the comment id from list_comments, and status must be one of open, in_progress, or done. Set it to in_progress when you start work and done when the change ships, closing the loop back to the PM. Returns nothing on success. |
propose_change |
no_return_description |
Submit the modified UI for a comment: the rewritten HTML (and optional CSS) that resolves the PM's request. Provide the comment id from list_comments, the modified html, and optional css and notes. This stores your proposal on the comment so the dev team can review the code and a live preview in the dashboard, and returns confirmation that the proposal was saved. Use get_comment first to see the original element, its computed styles, and the screenshot. |
Selection evidence
Confusable tool pairs.
0 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
| No confusable tool pairs were flagged in this assessment. | |||
Compare the field