Public leaderboard

Public assessment

beshogun/planwire-mcp (planwire-mcp)

planwire-mcp · v0.1.4 · scanned

What changed in the harness

Selection accuracy 98→100, token cost up 5%, 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

28.3 / 30

28.3 out of 30
03Economics

20.0 / 20

20.0 out of 20
04Discoverability

14.1 / 20

14.1 out of 20

Highest-impact fix

Estimated gain +6 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.

3 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
nearby_planning_applications
no_return_description
Find planning applications located within radius_km of a latitude/longitude point (WGS84). Use for questions like what's been applied for near this location. Returns the matching applications, each with its address, description, reference, status, and dates.
get_planning_application
name_restates_behavior no_return_description
Fetch the full record for a single planning application by its PlanWire id. Use after search_planning_applications or nearby_planning_applications to inspect one specific application in detail. Returns the application's address, description, reference, status, and dates for the given id.
list_councils
no_return_description
List the UK councils (local planning authorities) that PlanWire covers. Returns each council with its name and ID, which you can pass as the council parameter of search_planning_applications. Use to discover valid council values before searching.

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
search_planning_applications nearby_planning_applications medium Both tools return planning applications but differ only in location mechanism: search filters by postcode/council text while nearby requires lat/lng plus radius. A task phrased 'find planning applications near postcode OX1' or 'search for applications near me' contains both trigger words ('search', 'near'); the agent could plausibly pick search (which accepts postcode directly) or nearby (which matches 'near' semantically but needs coordinates), making the wrong selection likely without clarification.

Compare the field

One score is useful.
The evidence makes it actionable.

Back to the leaderboard