Skip to main content
Glama
CarlxsMG

UEAgent

by CarlxsMG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

remove_mapping_from_context

Destructive

Unbind a key from an InputAction in a saved Enhanced Input mapping context to resolve conflicting mappings or retire a verb while saving the mapping context to disk.

Instructions

Unbind a key from an InputAction in a saved Enhanced Input mapping context -- how you free a key that list_all_input_mappings flagged as conflicting, or retire a verb. Identified by context + action + key, so only the first mapping of that action to that key goes; the assets themselves survive. The engine moves the context's last mapping into the freed slot, so mapping indexes (add_input_trigger, list_input_triggers) can change. The context is saved, and a removal succeeds only when it reaches disk; a mapping that is not there succeeds with removed false and already_absent true, and saves nothing.

Returns: { context_name, action_name, key, removed, already_absent, mapping_count, saved, save_error? }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoKey name of the mapping to remove.
key_nameNoInput key name (e.g. SpaceBar, Gamepad_FaceButton_Bottom)
action_nameNoShort asset name of the InputAction.
action_pathNoAsset path of the Input Action
context_nameNoShort asset name of the InputMappingContext.
context_pathNoAsset path of the Input Mapping Context

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.0
    • removedInput schema / required
      Removed value: -[
-  "context_name",
-  "action_name",
-  "key"
-]
  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?

Goes well beyond the annotations (which only mark it destructive/non-idempotent) by disclosing non-obvious behavior: assets survive, dropping the last mapping shifts indexes used by add_input_trigger/list_input_triggers, the removal only succeeds once written to disk, and an absent mapping returns removed=false / already_absent=true without saving. This is the kind of side-effect detail an agent cannot infer from structured fields.

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 the action and use case before drilling into edge cases and the return shape. Dense but nearly every sentence carries information an agent needs; the mid-sentence parentheticals make it slightly heavy to scan.

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?

No output schema exists, but the description supplies the full return shape (removed, already_absent, mapping_count, saved, save_error), and the annotations cover the safety profile. For a destructive, non-idempotent mutation tool this is complete enough to call correctly.

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 already 100%, so the baseline is 3, but the description adds the useful composite identification model ('context + action + key') that explains how the six loosely-named params map to a single logical target. It stops short of clarifying the name-vs-path parameter pairs, so a 4 rather than 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?

States a specific verb (unbind/remove) and resource (a key-to-InputAction mapping in a saved Enhanced Input mapping context). It clearly distinguishes itself from siblings by naming list_all_input_mappings as the diagnosing tool and describing the exact removal granularity ('only the first mapping of that action to that key goes').

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 concrete triggering scenarios -- freeing a key list_all_input_mappings flagged as conflicting, or retiring a verb -- which routes the agent from the diagnostic tool to this one. No explicit when-not-to-use or exclusion conditions are stated, keeping it just short of a 5.

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