Skip to main content
Glama
Beckett — MCP for Godot

Beckett — MCP for Godot

by beckettlab

set_property

Destructive

Set a property on a resolved Godot object with undo support. Values are converted to the declared type and validated before writing, so incompatible input returns an error and changes nothing.

Instructions

Set a property on a resolved object (undoable). value is converted to the type the property declares: vectors take [x,y,z], "x y z" or "(x, y, z)", colors "#rrggbb", a name or [r,g,b,a], an enum its number, an object property a res:// path (loaded) or null. A value that does not fit is an ERROR and nothing is written. Every spelling: help(tool="set_property").

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": {
      "target": "<target>",
      "property": "<property>",
      "value": "<value>"
    },
    "name": "set_property"
  }
}

Input Schema

NameRequiredDescriptionDefault
saveNoalso write the resource's own .tres/.res file now
valueYesany JSON value
targetYes
propertyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.0
    • addedInput schema / properties / save
      Added value: +{
      +  "description": "also write the resource's own .tres/.res file now",
      +  "type": "boolean"
      +}
  2. Addedv1.12.1
  3. Removedv1.10.0
  4. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description adds value on top: "(undoable)" reassures the agent the mutation is reversible, and "A value that does not fit is an ERROR and nothing is written" discloses atomicity on failure. The save parameter's interaction with the resource file is only hinted at via the schema, not the description.

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?

Purpose and undoability are front-loaded, then the format table follows in one dense but scannable sentence. The trailing help() pointer is a reasonable escape hatch, though the value-format clause packs a lot into a single run-on sentence.

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

Completeness4/5

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

For a destructive mutation with no output schema, the description covers reversibility, failure atomicity, type coercion rules, and the save side-effect path. The notable remaining gap is how to obtain a valid target reference (which sibling produces one) and what the return value looks like on success.

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 only 50% — target, property, and value are undocumented in the schema — and the description compensates well for the highest-risk one by enumerating exact accepted formats for vectors, colors, names, enums, and resource paths, plus the null case. target and property remain unexplained beyond "resolved object" and "the type the property declares", which keeps it from a 5.

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?

States a specific verb and resource — setting a property on a resolved object — and adds the important qualifier that the change is undoable. It does not explicitly distinguish itself from near-siblings like set_resource or set_project_setting, so an agent must infer that this targets an in-memory object rather than a resource file or project setting.

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 context is implied by "resolved object" (i.e., the target must already be resolved, presumably via find_nodes/describe_object), but the description never says when to prefer this over set_resource, set_project_setting, or script_patch. The error-on-mismatch rule is a useful guardrail but is not usage routing.

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