material_manage

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

With no annotations provided, the description carries full burden. It discloses behaviors such as file creation (.tres), property setting with enum name acceptance, and undo grouping for apply_to_node. It mentions texture properties accept res:// paths. However, it lacks details on side effects like persistence behavior, error handling, or permission requirements. Overall, it provides substantial transparency beyond a bare description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is long (over 20 lines) and includes some redundancy, such as repeating the type parameter across multiple operations. It is structured with bullet points and front-loads the material types, but could be more concise by consolidating common parameter patterns. Every sentence arguably earns its place, but the length detracts from quick scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (8 operations), opaque schema parameters, and no annotations, the description is fairly complete. It explains each operation's parameters and behavior clearly. An output schema exists but is not shown; per rules, return value explanation is not required. The description covers the main aspects for an agent to use the tool effectively, though some edge cases (e.g., error conditions) are not addressed.

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

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

Schema coverage is 0%, meaning the schema parameters (op, params, session_id) have no descriptions. The description compensates fully by detailing the operation-specific parameters within each bullet point (e.g., for create: path, type, shader_path, overwrite). It explains that enum params accept names, color/vector are dicts, and texture properties accept res:// paths. This adds significant meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool is for 'Material authoring' and lists specific material types (StandardMaterial3D, ORMMaterial3D, ShaderMaterial, CanvasItemMaterial). It enumerates eight distinct operations (create, set_param, set_shader_param, get, list, assign, apply_to_node, apply_preset), each with a clear verb and resource. This distinguishes it from sibling tools like node_set_property or script_manage, which operate on different resource types.

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

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

The description provides context on when to use each operation, e.g., 'prefer for active-session reads' for resource form, and explains the purpose of each op like 'High-level: build + set params + assign in one undo' for apply_to_node. However, it does not explicitly state when not to use this tool versus alternatives (e.g., when to use node_set_property instead) or mention prerequisites or required permissions.

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