01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 10%, 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
18.1 / 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 |
|---|---|---|
FLUX_1-schnell-infer |
name_restates_behavior params_unexplained no_return_description |
Generate an image from a text description using the FLUX.1-schnell text-to-image model. prompt is the text that describes the desired image; seed sets the random generator seed, and randomize_seed controls whether a new random seed is used on each call. width and height set the output image dimensions in pixels, and num_inference_steps sets how many denoising/diffusion steps to run (more steps can improve quality at the cost of speed). Returns the generated image so it can be retrieved with the available-files tool. |
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