01Safety
0.0 / 30
What changed in the harness
Selection accuracy 98%, destructive-action safety rate 0% (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
28.3 / 30
03Economics
19.6 / 20
04Discoverability
15.3 / 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.
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.
4 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
port_info |
port_conflict |
high | Both take a single port and report the dev server blocking it; a task like 'what's on port 3000, is it free, and what should I do about it?' maps naturally onto either, especially when the user mentions EADDRINUSE loosely without using that exact keyword. |
list_dev_servers |
find_zombies |
medium | Both read-only tools return server lists; a task like 'show me my dev servers that are wasting memory/abandoned' or 'which of my servers are not being used' could point to find_zombies (abandoned heuristic) or list_dev_servers (full detail), and find_zombies' default filtering makes the boundary non-obvious. |
port_info |
find_zombies |
medium | A task like 'check if anything zombie-like is sitting on port 3000' or 'is port 3000 held by an abandoned server' blends the single-port query of port_info with the abandonment detection of find_zombies; neither name makes the port-scoping requirement explicit. |
list_dev_servers |
port_info |
medium | Both are read-only tools that report the dev server on a port with the same fields; 'what's running on port 3000/what servers are on which ports' could be answered by listing all servers, and the agent must notice port_info's single-port scope and required argument to disambiguate. |
Compare the field