01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→98, token cost down 0%, 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
29.4 / 30
03Economics
19.9 / 20
04Discoverability
10.9 / 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 |
|---|---|---|
glm_status |
no_return_description |
Free local status check that makes no GLM call. Takes no parameters. Returns the current peak-pricing window, the active model, a GLM usage ledger showing tokens spent as proof of GLM usage, and config health information. |
Selection evidence
Confusable tool pairs.
3 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
glm_agent |
glm_recommend |
low | Both relate to choosing/using GLM, but glm_agent executes repo work while glm_recommend only advises which engine to use; a task phrased as 'should I use GLM for this?' could plausibly trigger either, though descriptions make the distinction fairly clear. |
glm_agent |
glm_status |
low | Low overlap in purpose (execution vs. free status/ledger check); confusion is unlikely since glm_status has no task-execution semantics, but a vague 'check on GLM' request could momentarily brush against either. |
glm_recommend |
glm_status |
low | Both are free local/no-call advisory tools sharing 'glm', 'model', 'free', 'local' tokens, so a request like 'what's the current GLM setup/model recommendation' could blur between checking status vs. getting a recommendation, though their outputs (advice vs. ledger/config) differ clearly. |
Compare the field