Public leaderboard

Public assessment

tjclaude88/mcp-bling (bling-bag)

bling-bag · v0.1.0 · scanned

What changed in the harness

Selection accuracy 100→95, token cost up 2%, 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.

01Safety

0.0 / 30

0.0 out of 30
02Legibility

29.2 / 30

29.2 out of 30
03Economics

20.0 / 20

20.0 out of 20
04Discoverability

14.0 / 20

14.0 out of 20

Highest-impact fix

Estimated gain +30 points

Add 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
get_theme_for_platform
no_return_description
Returns your bot's theme colours formatted for the requested platform as a string. 'terminal' yields ANSI escape codes, 'web' yields CSS variables, and 'slack', 'discord', and 'ide' yield their platform-specific formats; any other platform value returns the raw hex colours.

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_identity roll_identity medium A task like 'give me your bot's identity' or 'get an identity for your bot' is ambiguous: get_identity fetches the configured identity, while roll_identity generates a new random one. Both descriptions center on the bot's identity (name, personality, appearance), so an agent could pick the wrong member without a verb like 'roll' or 'current' in the request.
get_identity get_theme_for_platform medium A task such as 'show me what your bot looks like' or 'get your bot's theme/appearance' is ambiguous: get_identity returns appearance and theme colours, while get_theme_for_platform returns colours formatted for a platform. Both begin with 'get' and overlap on bot/your tokens, so a request about look or colours could route to either tool.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard