mmar_create_class

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

No annotations are provided, so the description carries the full burden. It does disclose the incremental add behavior (rather than recreating the whole SceneType) and details required fields in class_data. However, it does not mention return values, error handling, or prerequisites like the SceneType existing. This is a moderate level of transparency for a mutation tool.

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 appropriately sized: a two-sentence overview with a concise bullet-like list of required fields. It is front-loaded with the primary purpose and contains no filler or redundant information.

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?

The tool has no output schema, so the description should ideally cover what the tool returns or confirms. It doesn't. It also omits validation behavior and prerequisites. However, it does convey the core operation and required parameters, making it sufficient for basic invocation but not fully complete for an agent anticipating outcomes.

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?

The input schema already describes both parameters with 100% coverage. The description adds value by specifying the exact required keys inside class_data (uuid, name, geometry, is_reusable, is_abstract, attributes, ports) and clarifies that geometry can be null and attributes/ports are arrays. This goes beyond the schema's 'including uuid, name, attributes, ports, geometry' and covers missing fields.

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 function: 'Create a new class (node/shape type) and add it to an existing SceneType.' It uses a specific verb (create) and resource (class), and distinguishes from siblings by emphasizing 'instead of recreating the whole SceneType.' This differentiates it from scene-type-level creation and update operations.

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?

Explicit guidance is provided: 'Use this for incremental metamodel building instead of recreating the whole SceneType.' This gives a clear when-to-use context and an alternative to avoid, directly helping the agent decide between this tool and others like update_scene_type or create_scene_type.

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