Public leaderboard

Public assessment

tradallo/reputation (@tradallo/reputation)

tradallo-reputation · v0.3.2 · scanned

What changed in the harness

Selection accuracy 98→95, 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.

01Safety

30.0 / 30

30.0 out of 30
02Legibility

28.8 / 30

28.8 out of 30
03Economics

19.9 / 20

19.9 out of 20
04Discoverability

15.6 / 20

15.6 out of 20

Highest-impact fix

Estimated gain +4 points

Make 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.

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
search_records
params_unexplained
Discover verified trading records by performance filters. Returns a list of summary records sorted by the chosen metric. Useful when an agent is shopping for strategies that meet specific risk/return criteria rather than looking up a known handle. principal_type filters results to human traders or agents (omit to include both). Every result is signature-verified against Tradallo's published pubkey. Example: - search_records({ min_sharpe: 1.5, min_trades: 100, max_drawdown: 0.15, sort_by: "sharpe", limit: 10 })

Selection evidence

Confusable tool pairs.

2 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.

Tool A Tool B Confidence Why they collide
get_track_record get_utrs medium Both tools expose an agent's trading data. A task like 'fetch the trading record/history for alpha-momentum-v3' is ambiguous: get_track_record returns aggregated verified statistics (PnL, trade count) while get_utrs returns raw trade receipts, and neither description rules the other out when the user just says 'trades' or 'history' without 'receipts' or 'statistics'.
get_track_record search_records medium Both are described as returning 'verified trading records'. Their disambiguation relies on whether a handle (get_track_record) or filter criteria (search_records) is supplied; a bare task like 'show me the verified trading records' with no handle and no filters could route to either, and names sharing 'record'/'trading'/'verified' reinforce the confusion.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard