omni_shape_building

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions structural components and optional foundation, but it does not state that the tool places/blocks the world, whether it replaces existing blocks, what happens with door positioning relative to doorSide, or any side effects of the one-call operation. This leaves an agent guessing about mutative consequences.

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 two short sentences, front-loaded with the core concept and then reinforced with concrete example user intents. There is no repetition, filler, or unnecessary detail; every sentence contributes to tool selection.

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 is highly complex (24 parameters, 4 required), has no output schema, and no annotations, yet the description only captures the high-level purpose and use cases. It omits operational details like how width/depth/height map to the structure, how roof styles behave, how the centered door relates to doorSide, and what window band parameters control. An agent could select the tool from this description, but it would not be confident about correct invocation.

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 description coverage is only 8% for 24 parameters, so the description would need to compensate heavily. It does add some semantic context by listing house components (foundation, floor, walls, roof, door, windows), and it clarifies the foundation is optional, but it does not map these components to the many parameters or explain key options such as roofStyle, doorSide, or windowsEnabled. This is insufficient for a tool with this many undecumented parameters.

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 identifies the tool as a one-call generator for a complete house-like structure, listing the concrete components it creates (foundation, floor, walls, roof, centered door, window band). It also gives explicit natural-language triggers ('build me a house', 'build me a tower', 'build me a small castle'), which distinguishes it from the sibling individual-shape tools such as omni_shape_solid_box or omni_shape_gable_roof). It lacks a direct verb like 'builds', but the intent is unmistakable.

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 gives explicit when-to-use guidance by naming the exact user requests it answers, which is strong signal for an agent deciding between this and the more granular shape primitives. It does not name explicit alternatives or exclusion conditions, so it misses the 'when not to use' half of ideal usage guidance.

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