Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

map_input_action

Destructive

Binds a key to an Enhanced Input action in an input mapping context using full asset paths and saves the context, so agents can add verified mappings to Unreal Engine input assets.

Instructions

Bind a key to an InputAction in an Enhanced Input mapping context, both by full asset path (add_mapping_to_context takes short names), and save the context. A context that already maps that key to that action is left as it is (added false, already_mapped true, not saved); a new mapping succeeds only when the context reaches disk. Other actions on the same key are not checked: use find_free_input_key or list_all_input_mappings first.

Returns: { context_path, action_path, key_name, index, mapping_count, added, already_mapped, saved, save_error? }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoAlias of key_name, read only when key_name is absent (same FKey names).
key_nameNoKey name to map (e.g., "SpaceBar", "LeftMouseButton").
action_pathNoFull path to the InputAction asset.
context_pathYesFull path to the InputMappingContext asset.
input_action_pathNoFallback for action_path when action_path is absent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.0
    • changedInput schema / properties / key / description
      Previous value: -"Key name"New value: +"Alias of key_name, read only when key_name is absent (same FKey names)."
    • changedInput schema / required
      Previous value: -[
-  "context_path",
-  "action_path",
-  "key_name"
-]New value: +[
+  "context_path"
+]
  2. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and non-idempotent, but the description adds the exact duplicate-handling semantics (added false, already_mapped true, not saved) and the success criterion (a new mapping succeeds only when the context reaches disk). It also exposes save_error as an output field, giving real behavioral context beyond the annotations.

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?

The purpose sentence, the sequencing note, and the compact Returns block are front-loaded with little waste, though the first sentence is dense and merges the path distinction with the save behavior in one clause. Slightly tighter phrasing would earn a 5.

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?

There is no output schema, so the description supplies the full return shape and the save-failure field. Combined with the prerequisite guidance for key collisions and the mutation/idempotency semantics, an agent has everything needed to call this correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents key/key_name aliasing and the action_path fallback. The description reinforces that these must be full asset paths, which is a useful nuance, but it does not add syntax or format detail the schema lacks. Baseline 3 applies.

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 (bind) and resources (key, InputAction, mapping context) and explicitly distinguishes itself from the sibling add_mapping_to_context by noting the full-asset-path vs short-name difference. An agent can identify this tool without opening any schema.

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

Usage Guidelines5/5

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

Explicitly names the alternative add_mapping_to_context and the condition that separates them (full paths vs short names), and routes the agent to find_free_input_key or list_all_input_mappings as a prerequisite when other actions on the same key matter. Both when-to-use and when-to-consult-other-tools are stated.

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

Deploy Server

Other Tools