01Safety
30.0 / 30
What changed in the harness
Selection accuracy 100%, destructive-action safety rate 100% (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.
02Legibility
29.7 / 30
03Economics
20.0 / 20
04Discoverability
13.4 / 20
Highest-impact fix
Estimated gain +7 pointsMake target tools discoverable on the first call
Clarify tool names, decision boundaries, and required argument schemas so an agent can choose and construct the target call without exploratory steps.
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.
1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
search_registry |
get_instruction |
medium | Both operate on the same OpenClaw instruction registry and natural phrasing like 'find/get the [X] instruction' appears in both descriptions (search_registry: 'find system prompts, skills...'; get_instruction: 'Fetch a complete instruction file... by slug'). Since get_instruction requires a slug the agent may not yet have, a discovery task ('show me the web-research instructions') could wrongly trigger get_instruction with a guessed slug, while a retrieval task could wrongly trigger search_registry, which only returns metadata rather than the full deployable instruction content the user wants. The registry framing overlaps enough to make the boundary ambiguous unless the documented two-step flow (search first, then fetch) is explicitly followed. |
Compare the field