Skip to main content
Glama

activate_ability

Destructive

Activates a granted ability on an editor-world actor's ability system component and reports if the engine accepts the activation. Grant the ability first; cancel it to stop.

Instructions

Try to activate one granted ability on an editor-world actor ability system component with TryActivateAbility; activated is the engine verdict, false when the activation checks of the ability refuse it. Use grant_ability first, and cancel_ability to stop it.

Returns: { actor_name, ability_name, activated }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actor_nameYesObject name (not the label) of the editor-world actor, e.g. "BP_Hero_C_1", matched case-insensitively; find_actors_by_name maps labels to names
ability_nameYesAbility to match among the granted specs: the ability_name from get_active_abilities, the class name with or without _C ("GA_Jump"), the asset path ("/Game/Abilities/GA_Jump") or the class path; case-insensitive, first match wins

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.0
    • changedInput schema / properties / ability_name / description
      Previous value: -"Name of the ability to activate"New value: +"Ability to match among the granted specs: the ability_name from get_active_abilities, the class name with or without _C (\"GA_Jump\"), the asset path (\"/Game/Abilities/GA_Jump\") or the class path; case-insensitive, first match wins"
    • changedInput schema / properties / actor_name / description
      Previous value: -"Name of the actor whose ability to activate"New value: +"Object name (not the label) of the editor-world actor, e.g. \"BP_Hero_C_1\", matched case-insensitively; find_actors_by_name maps labels to names"
  2. First observedv1.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description earns extra credit by explaining the failure mode: activated is the engine verdict and is false when the ability's own activation checks refuse it, so a false result is not an error. It does not explain what state change makes this 'destructive' or any cooldown/cost/tag gating, but the activation-check semantics go meaningfully 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, followed by prerequisite/alternative routing, then a compact returns line. Two sentences plus the return spec, with no filler.

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 2-parameter action tool with no output schema, it supplies purpose, prerequisite, cleanup, and the return shape, which is nearly complete. Minor gaps remain (whether PIE/world context is required, and why the operation is destructive), but nothing essential for calling it correctly is missing.

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%, and both actor_name and ability_name are thoroughly documented there (case-insensitive matching, name vs label, alternate path forms). The description adds no parameter-level detail, so the baseline of 3 is appropriate.

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 (activate one granted ability on an editor-world actor's ability system component) and names the concrete engine call TryActivateAbility, so an agent understands exactly what happens. It is readily distinguishable from siblings like grant_ability, cancel_ability, and get_active_abilities.

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 routes the agent: 'Use grant_ability first, and cancel_ability to stop it.' That gives both a prerequisite condition and the alternative tool for the opposite operation, leaving nothing to inference.

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