01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 2%, 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
29.8 / 30
03Economics
19.7 / 20
04Discoverability
12.7 / 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.
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 |
|---|---|---|
extractDom |
no_return_description |
Extract HTML, text, and DOM structure from a webpage into a structured result. USE WHEN: Need text content for analysis, DOM structure for selector discovery, or pre-capture page validation. USE captureScreenshot WHEN: Need visual verification or rendered UI. RETURNS: The extracted page content — HTML, plain text, and element structure — scoped to the optional CSS selector, or the entire document if no selector is given. • url (required): Page URL • selector (optional): CSS selector to scope extraction (e.g., 'main', 'article'). Omit for entire document. EXAMPLE: { "url": "https://example.com", "selector": "article" } |
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