Public leaderboard

Public assessment

davidmosiah/astral-mcp (astral-mcp)

astral-mcp · v0.3.0 · scanned

What changed in the harness

Selection accuracy 98%, destructive-action safety rate 100% (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.

01Safety

30.0 / 30

30.0 out of 30
02Legibility

29.0 / 30

29.0 out of 30
03Economics

15.4 / 20

15.4 out of 20
04Discoverability

12.6 / 20

12.6 out of 20

Highest-impact fix

Estimated gain +7 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.

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
astral_capabilities astral_agent_manifest medium Both are onboarding/meta documentation describing the 'read me first, recommended workflow/first calls' purpose, so a general request like 'how do I get started' or 'what's the recommended call sequence' maps plausibly to either.
astral_demo astral_capabilities low A request to 'show me an example of what you can produce' could route to the demo (sample payload) or to capabilities (feature overview), though descriptions mostly disambiguate example-output from feature-list intents.
astral_current_transits astral_data_inventory low Both names and descriptions surface 'transit(s)' — inventory even lists transits as a data domain — so a task phrased as 'what transit data is available' could route to the inventory instead of the compute tool; direct compute requests remain clear.
astral_current_transits astral_synastry low Both compute aspect charts from birth data; a task framed as 'compare/check the aspects for me' is ambiguous between current transits and a partner synastry reading, though 'two people' vs 'current/upcoming' wording mostly resolves it.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard