0.0 / 30
What changed in the harness
Selection accuracy 100%, destructive-action safety rate 0% (baseline only -- no rewrite pass applied).
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.
01Safety
02Legibility
29.4 / 30
03Economics
19.7 / 20
04Discoverability
20.0 / 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.
0 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 |
|---|---|---|
| No description defects were flagged in this assessment. | ||
Selection evidence
Confusable tool pairs.
4 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
generate_diagram_from_ascii |
generate_diagram_from_mermaid |
medium | Both accept text-based diagram source with arrows/box-like syntax; a user pasting Mermaid-like or borderline ASCII-arrow code without saying 'mermaid' or 'ascii' could route to the wrong converter. |
generate_diagram_from_text |
generate_diagram_from_json |
low | If a user describes JSON-like data in prose ('visualize this data: {...}') without pasting raw JSON, the agent might pick generate_diagram_from_text since it's the default/catch-all for descriptions, though JSON tool is more specific when raw JSON is present. |
generate_diagram_from_json |
generate_diagram_from_ascii |
low | Both take structured 'content' strings; minor risk if user pastes a JSON-formatted tree that resembles ASCII layout, but JSON's distinct syntax makes confusion unlikely. |
generate_diagram_from_image |
generate_diagram_from_mermaid |
low | Low overlap since one requires an image URL/base64 and the other text-based Mermaid source — an agent could only confuse these if a task vaguely says 'convert this diagram' without clarifying the source format. |
Compare the field