01Safety
0.0 / 30
Public leaderboard
Public assessment
recursechat/mcp-server-apple-shortcuts (mcp-server-apple-shortcuts)
What changed in the harness
Selection accuracy 100→100, token cost up 14%, 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
28.9 / 30
03Economics
20.0 / 20
04Discoverability
10.7 / 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.
2 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 |
|---|---|---|
run_shortcut |
name_restates_behavior no_return_description |
Trigger an existing Shortcuts automation by its name and wait for it to complete; optionally pass an input string that the shortcut receives. Use this to run a pre-configured automation rather than building one inline. Returns the outcome or result produced by the shortcut run. |
list_shortcuts |
name_restates_behavior no_return_description |
Return every Shortcuts automation currently available to this server so callers can discover exact shortcut names before invoking run_shortcut. Use this to enumerate the available automations and their identifiers. |
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 |
|---|---|---|---|
run_shortcut |
list_shortcuts |
low | The descriptions clearly separate actions: one runs a named automation, the other lists all shortcuts. Tasks like 'show my shortcuts' map to list_shortcuts and 'run my morning shortcut' map to run_shortcut; the verb alone disambiguates, so no natural-language task plausibly causes a wrong pick. |
Compare the field