Skip to main content
Glama
Beckett — MCP for Godot

Beckett — MCP for Godot

by beckettlab

batch_execute

Run multiple Godot tool calls in one ordered request, stopping at the first failure and rolling back scene edits, to collapse multi-step authoring into one atomic call.

Instructions

Run several tool calls in one request, in order. steps = [{tool, args}]. Stops at the first failure (stop_on_error, default true). When a step fails, scene edits made by the batch are rolled back via the editor undo history (rollback, default true); file/resource writes are not. Use to collapse multi-step authoring (create node → set props → attach script) into one atomic call. ok per step means the handler completed - verify EFFECTS with a trailing read-back step (a get_* or describe_object call; assert_scene / assert_node_state in Full) before trusting a mutation batch.

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": {
      "steps": "<steps>"
    },
    "name": "batch_execute"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYesordered [{tool: name, args: {...}}]
rollbackNoundo scene edits on failure (default true)
stop_on_errorNohalt on first failure (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.10.1
  2. Removedv1.10.0
  3. First observedv1.0.0

TDQS

A4.7/5.0
Behavior5/5

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

Discloses non-obvious behavior well beyond the annotations: sequential execution, stop-on-first-failure by default, and a nuanced rollback story — scene edits are undone via editor undo history while file/resource writes are NOT rolled back. It also warns that a per-step 'ok' only means the handler returned, not that the effect landed. Consistent with readOnlyHint=false and destructiveHint=false.

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?

Front-loaded with purpose, then failure/rollback semantics, then the verification advice — every sentence carries substance. Slightly dense with stacked parentheticals, and the reference to 'Full' and assert_scene / assert_node_state is unexplained clutter for an agent without that context.

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 batch-dispatch tool with no output schema, the description covers the essentials an agent needs to call it safely: input shape, ordering, failure halt, rollback scope, and the reliability limit of per-step success. Nothing material is missing.

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

Parameters5/5

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

Schema coverage is already 100%, yet the description still adds meaning: the exact step element shape ({tool, args}), that both rollback and stop_on_error default to true, and critically that rollback's scope is limited to scene edits and excludes file writes. That scoping detail is not derivable from the schema.

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?

States a specific verb and resource — run several tool calls in one ordered request — and immediately gives the argument shape (steps = [{tool, args}]). It is clearly distinguishable from every single-operation sibling such as create_node or set_property by framing itself as the aggregator for multi-step authoring.

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?

Explicitly tells the agent when to reach for it: to collapse multi-step authoring (create node → set props → attach script) into one atomic call. It adds a usage caveat about verifying mutation batches with a trailing read-back step, but does not state when NOT to batch (e.g. independent or conditional operations).

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