01Safety
0.0 / 30
What changed in the harness
Selection accuracy 97→92, token cost down 21%, 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
29.0 / 30
03Economics
19.9 / 20
04Discoverability
18.8 / 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.
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 |
|---|---|---|
metadata |
no_return_description |
Extract metadata from any webpage and return it as a JSON object containing the page's title, description, Open Graph tags, Twitter Cards, JSON-LD structured data, favicon, canonical URL, and more. |
run_tool |
no_return_description |
Run any Junipr API tool by its slug and return that tool's result, typically a JSON object (or base64-encoded data for document/image tools). Pass any parameters the tool accepts as a JSON object in the "input" field. 75+ tools are available across validation, conversion, analysis, scraping, and data extraction categories; full docs: https://junipr.io |
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