Skip to main content
Glama

krusch_run

Stage proposed file edits as a unified diff and run the pre-commit invariant gate without modifying the working tree, enabling safe validation before applying changes.

Instructions

Stage proposed file edits as a unified diff and run the pre-commit invariant gate without mutating the working tree.

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": {
      "goal": "<goal>"
    },
    "name": "krusch_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYes
editsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.1

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and the description usefully clarifies that the working tree is not mutated (staging only). However, it omits key behavior: what happens when the invariant gate fails, whether staged diffs persist for a later apply, and whether repeated calls compound. For a non-idempotent, non-read-only tool that is a meaningful gap.

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?

One front-loaded sentence with the action and its key safety constraint, no filler. It is dense with domain terms ('invariant gate', 'unified diff') that could be traded for one clarifying clause, but nothing is redundant.

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

Completeness2/5

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

With no output schema, 0% param coverage, and no explicit statement of the gate's pass/fail result shape or the staging lifecycle, the description is thinner than the tool's complexity warrants. An agent knows what the call does at a high level but not what it gets back or how to use the result.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must carry parameter meaning and it largely does not. It implies that 'edits' are the proposed file changes, but never explains that each edit carries a file_path and full content, nor does it mention the required 'goal' parameter at all.

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

Purpose4/5

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

The description states a specific verb+resource pair ('stage proposed file edits as a unified diff') plus a second action ('run the pre-commit invariant gate'), which distinguishes it from the siblings that apply or display diffs. The term 'invariant gate' is domain jargon that is not unpacked, so an agent unfamiliar with the workflow may not fully grasp what is being checked.

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?

Usage is implied rather than stated: 'pre-commit' and 'without mutating the working tree' suggest this is the safe preview step before an apply, but the description never names krusch_apply_diff or krusch_reject as the follow-up alternatives, nor does it say when to skip this and go straight to applying. Adequate but leaves routing to inference.

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