01Safety
30.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 7%, unconfirmed writes 100%→100%.
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
29.5 / 30
03Economics
20.0 / 20
04Discoverability
20.0 / 20
Highest-impact fix
Estimated gain +1 pointRewrite 1 underspecified tool description
State each tool's behavior, explain every parameter, and declare return semantics, prioritizing tools exercised by failed selection tasks.
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 |
|---|---|---|
get_jobs |
name_restates_behavior no_return_description |
Retrieve available job postings, optionally filtered by how recently they were posted (sinceWhen, e.g. '1d' or '1w'), matching the given keywords, excluding any posting that contains one of the excludeKeywords, and restricted to remote positions when isRemote is true. Returns the list of job results that satisfy the active filters. |
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