Skip to main content
Glama

What a change reaches, and what to run

godot_impact
Read-onlyIdempotent

Trace edited files backward through the project graph to every affected scene, autoload, test, and scenario, then get the exact checks to run before declaring the work done.

Instructions

The blast radius of a change, offline: from the changed files (default: everything that differs from git HEAD, new files included; or files) backwards through the project's file graph (ext_resource, preload, class_name, includes, and paths the code loads later) to every scene that loads them, nearest first with the chain in between and the main scene marked; whether the change is global (an autoload or something an autoload loads, project.godot, a class_name many scripts use); the test files and saved scenarios that cover it; deleted files something still names; then the numbered checks to run for exactly this change (godot_review with the files, godot_check, the scenarios, the tests, the scene to play). Call it when you finished a set of edits, before you say the work is done: checking only the file you edited misses the scenes that instance it. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "godot_impact"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNothe commit to compare with when files is not given (default HEAD)
pathNoproject folder, or a file or folder inside it (relative to the server's folder; default: the current project)
filesNothe changed res:// files (default: what differs from ref in git)
detailNobrief (capped lists) or full (everything); default full

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only/idempotent/closed-world, and the description still adds substantial behavior: the default input set is the git diff against HEAD including new files, traversal is backwards through the file graph, results are ordered nearest-first with the chain and main scene marked, and it surfaces globality, deleted-file references, and covering tests/scenarios. This is exactly the kind of extra context that annotations cannot carry.

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?

Content is front-loaded and every clause carries information (inputs, traversal, ordering, globality, deleted refs, follow-up checks) with no filler. The downside is that it is a single semicolon-chained mega-sentence with nested parentheticals, which is denser than it needs to be; splitting it would improve scanability without losing content.

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

Completeness5/5

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

For a read-only analysis tool with no output schema, the description fully specifies what comes back: nearest-first scenes with chains, main scene marked, global-change flag, covering tests/scenarios, dangling references, and a numbered action list. Nothing an agent needs before calling or interpreting results is missing.

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%, so the baseline would be 3. The description nevertheless adds meaning beyond the schema by explaining what the `files` default actually resolves to ('everything that differs from git HEAD, new files included') and ties `ref` to that default. It says nothing about `detail` or `path` beyond the schema, so not a 5.

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

Purpose5/5

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

Leads with a specific noun+action framing ('The blast radius of a change, offline') and then enumerates the resources traversed (ext_resource, preload, class_name, includes, runtime-loaded paths). It is clearly distinct from the sibling check runners it names (godot_check, godot_review) because it computes reachability rather than performing the checks.

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

Usage Guidelines4/5

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

Gives an explicit trigger — 'Call it when you finished a set of edits, before you say the work is done' — plus the rationale ('checking only the file you edited misses the scenes that instance it'). It also routes forward to the follow-up tools (godot_review with the files, godot_check, scenarios, tests). There is no explicit when-not-to-use condition, which keeps it from a 5.

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