Loading ToolBench

Reading the current corpus…

runx MCP server · F · ToolBench

← Browse

runx

github.com/runxhq/runx

Native governed runtime for agent skills, tools, graphs, and packets with MCP server capabilities

2025-06-18+STDIO1 tools

40/100

Definition Quality20

Protocol Readiness50

Supportability67

Spec posture

Inferred effective spec 2025-06-18+·current baseline 2026-07-28

Static source inference · medium confidence · evidence: structured output

No deprecated protocol patterns detected

Summary

Single tool 'fixture_status' has critical definition gaps. Input schema is present but empty (no parameters documented). Description is minimal (18 chars: 'Return fixture status.'), below the 20-char hard floor for description scoring. No output schema visible in source. Tool appears to be a stub or test fixture rather than a production-grade MCP tool. No parameter descriptions, no error handling guidance, no composition hints. The tool definition is inferred from mcp.json rather than explicit Rust registration code, triggering the 50-point cap for inferred tools.

Tools (1)

fixture_statusread onlysource verified20/100

Return fixture status.

Issues (5)

CRITICALtool-description ↗

Description too short (18 chars). 'Return fixture status.' provides no context for when/why to call this tool.

fixture_status

CRITICALconstrained-input ↗

Input schema is empty object with no properties. No parameters documented. Unclear what the tool accepts or requires.

fixture_status

HIGHtool ↗

No output schema visible. LLMs cannot plan downstream calls or extract return values without knowing the response structure.

fixture_status

MEDIUMtool ↗

Tool name 'fixture_status' does not start with a clear action verb. 'get_fixture_status' or 'check_fixture_status' would be clearer.

fixture_status

HIGHtool ↗

Tool definition inferred from mcp.json config file, not explicit Rust registration. Cannot verify actual implementation or error handling.

fixture_status

Recommendations

Expand description to 50-200 chars. Example: 'Get the current status of the test fixture, including health, last update time, and any active issues. Call this before running tests to verify the fixture is ready.'
Document output schema explicitly. Specify what fields are returned (e.g., status: string, last_updated: ISO8601, is_healthy: boolean).
Rename tool to start with action verb: 'get_fixture_status' or 'check_fixture_status'.
If the tool accepts parameters, add them to the schema with type and description. If it truly accepts no input, document that explicitly in the description.
Add error handling guidance: 'If fixture is unhealthy, call reset_fixture() to reinitialize.'

Score history

Overall score trend

First recorded score · v2 rubric

40/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	40	2025-06-18+	v2