Skip to main content
Glama

game_art_direction

Define and save a game's art direction—gameplay, world, style notes, camera view, and construction—so future scene briefs use consistent visual guidance.

Instructions

Read/save gameplay, world, style_notes, view and construction for this game.

Interpret the user's description with the current AI host; do not require a form. view: isometric/top_down/third_person/first_person. construction: handcrafted/salvaged/machined. Partial updates retain omitted fields. detail: auto/readable/balanced/closeup; match_game_style learns from actual reference images. Text guides custom modeling; structured choices also affect recipe geometry/surfaces. This changes future briefs, not already imported assets. Use set_project_style for palette.

Input Schema

NameRequiredDescriptionDefault
settingsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.9.1

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose useful traits: 'Partial updates retain omitted fields' and that changes affect future briefs rather than already imported assets. However, it omits permissions/auth requirements, whether writes are reversible, and return behavior, which matters for a read/save tool with no output schema.

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-loads the purpose and packs field-value guidance efficiently with no filler. The terse 'view:'/'construction:' shorthand is dense but readable; a little structure (bullets) would help but nothing is wasted.

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 one-parameter tool with no annotations and no output schema, the description covers field semantics, partial-update behavior, and forward-scope effects, which is most of what an agent needs. Missing return/permission details are minor given the absence of an output schema.

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?

The single 'settings' parameter is an opaque object with 0% schema description coverage, so the description must compensate. It does so well, naming keys (view, construction, detail, style_notes) and enumerating allowed values (isometric/top_down/..., handcrafted/salvaged/machined, auto/readable/balanced/closeup), adding real meaning beyond the schema.

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 pair (read/save) and the resources it manages (gameplay, world, style_notes, view, construction) for 'this game', and distinguishes itself from set_project_style for palette. The scope is clear, though the exact field semantics of 'gameplay'/'world' remain a bit opaque.

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?

Provides one explicit alternative ('Use set_project_style for palette') and a scoping rule ('This changes future briefs, not already imported assets'), but gives no guidance on when to prefer it over close siblings like set_art_brief or set_scene_look. Usage is implied rather than fully specified.

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