01Safety
0.0 / 30
What changed in the harness
Selection accuracy 82→89, token cost up 11%, 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
25.7 / 30
03Economics
20.0 / 20
04Discoverability
12.8 / 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.
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 |
|---|---|---|
download_media |
no_return_description |
Downloads one or more files (images, videos, or other media) from URLs — typically ones found in auth_fetch results — using the browser's saved session cookies for authentication, so no re-login is needed. Saves each file to output_dir (or ~/.auth-fetch-mcp/downloads/<timestamp>/ if omitted) and returns the local file paths and download status for each URL. |
list_pages |
no_return_description |
Returns an array of all currently open browser tabs, each entry including its URL and page title, so callers can identify which tab to target for further actions. |
close_browser |
name_restates_behavior no_return_description |
Shuts down the browser window used by auth_fetch and download_media, freeing resources when no more page captures or downloads are needed. Login sessions/cookies persist to disk and are automatically restored the next time a browser is opened. Returns a confirmation once the browser process has closed. |
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