Public assessment

kehvinbehvin/json-mcp-filter (json-mcp-filter)

json-mcp-filter · v1.0.1 · scanned Aug 3, 2026

What changed in the harness

Selection accuracy 100%, 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

29.5 / 30

29.5 out of 30

03Economics

20.0 / 20

20.0 out of 20

04Discoverability

11.6 / 20

11.6 out of 20

Highest-impact fix

Estimated gain +8 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.

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

Tool A	Tool B	Confidence	Why they collide
`json_filter`	`json_dry_run`	medium	Both tools accept identical inputs (filePath plus a shape object) and describe working with a JSON structure via shape notation, so a task like 'check/analyze this JSON using this shape' is ambiguous: dry_run returns byte sizes while filter extracts data, and neither description sharply separates 'preview/size' from 'extract' without noticing the size-specific wording.
`json_schema`	`json_filter`	low	Descriptions are fairly distinct (generating a TypeScript schema vs extracting fields via a shape), but a task phrased as 'analyze/understand the structure of this JSON file' could plausibly route to either, since json_filter's description also says to analyse the JSON schema and both target a filePath/URL.
`json_schema`	`json_dry_run`	low	A vague task like 'analyze or break down this JSON file' could lead an agent to either tool: json_schema maps to structure/type analysis while json_dry_run maps to field-size analysis, though the schema-vs-bytes purpose split keeps the confusion weak.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard