Skip to main content
Glama

ghost_runner

Reproduce bugs with zero-assumption TDD: run a failing test before patching and verify it passes after.

Instructions

Zero-assumption TDD bug reproducer. Requires test to FAIL before patching, and PASS after patching.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "mode": "<mode>",
      "test_cmd": "<test_cmd>"
    },
    "name": "ghost_runner"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes'reproduce' expects failure, 'verify' expects success
test_cmdYesShell command to run reproduction test

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.0

TDQS

B3.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden; it does disclose the key gating rule (must fail first, pass second), which is real behavioral information. It omits what happens on a mismatch, whether the run is aborted, and that it executes an arbitrary shell command with the attendant safety implications.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with the core constraint front-loaded and no filler. It is efficient, though 'zero-assumption' is a bit of jargon that spends words without adding operational meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-required-parameter tool with no annotations and no output schema, the definition is minimal: it does not say what verdict or artifact is returned, how a failing command's output is surfaced, or what happens when the expectation is not met. The gating rule is present but the surrounding contract is not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the mode enum already documents both values, so the baseline is 3. The description adds a small amount by tying the expectations to workflow phases ('before patching' / 'after patching'), reinforcing what each mode asserts.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description labels the tool a 'TDD bug reproducer', which conveys intent, but never states the concrete action (running a shell test command and checking its exit status). The verb is implied rather than named, though the 'reproduce vs patch' framing does separate it from siblings like git_worktree_sandbox.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The fail-before-patch / pass-after-patch sequence implies a two-step workflow (reproduce, then verify), which is usable guidance. However, it never says when to prefer this over alternatives or what to do if the pre-condition is already satisfied, leaving the agent to infer the ordering.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.