01Safety
30.0 / 30
What changed in the harness
Selection accuracy 96→94, token cost down 0%, 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
28.5 / 30
03Economics
15.7 / 20
04Discoverability
19.0 / 20
Highest-impact fix
Estimated gain +4 pointsReduce the tool-definition and task token payload
Consolidate overlapping tools and trim repetitive schema text while preserving behavior, parameter, and return semantics.
Description evidence
Defects and rewrites.
3 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 |
|---|---|---|
search_artworks |
params_unexplained |
Search across registered open-access museum collections. Returns artwork records that pass source-specific rights verification (ambiguous records excluded by default). Supports an optional date-range filter for researcher queries like "Dutch genre painting 1640–1680". Use `limit` (integer, 1-50, default 10) to control how many matching records are returned. |
get_artwork |
no_return_description |
Fetch a single artwork by its normalized ID (e.g. met:436533). Returns the artwork's full cached record (title, artist, date, medium, image URL, rights/license status, and source museum), or an error if the ID does not resolve to a known record. |
cite |
no_return_description |
Render a citation for an artwork. Styles: "full" (artist, title, date, museum, license, URL), "caption" (image caption form), "short" (inline reference); defaults to "full". Returns the formatted citation as a plain text string. |
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