01Safety
0.0 / 30
What changed in the harness
Selection accuracy 98→98, 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
28.6 / 30
03Economics
20.0 / 20
04Discoverability
13.5 / 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 |
|---|---|---|
generate_report |
name_restates_behavior no_return_description |
Compile a market intelligence report from previously queried opportunity data into a standalone HTML document, optionally scoped to a given category or topic via the 'focus' parameter. Returns the complete HTML report as a string artifact for direct display. |
Selection evidence
Confusable tool pairs.
1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
render_report |
generate_report |
high | Both produce a full HTML report and share near-identical phrasing ('full HTML ... report with all ranked/discovery opportunities'), so a task like 'generate the discovery report' could plausibly route to either; the key distinguishing detail (render_report requires pre-fetched ideas augmented with a narrative object, while generate_report just takes an optional focus string) is easy to miss without careful schema inspection. |
Compare the field