Create slabs

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

Annotations declare write/idempotent=false but the description adds substantial behavior beyond them: one undo step, that a failing item does not abort the others, the per-item return shape [{guid,type}|{error}] in input order, automatic polygon regularization, and that localized attribute names must be looked up via get_attributes. This is rich, non-obvious disclosure 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?

Dense but front-loaded: the first sentence states purpose and geometry, followed by units, defaults, return shape, and read-back guidance, which is defensible given 40+ nested parameters. A few sentences restate schema field descriptions (e.g., the level/referencePlane definition), mildly inflating length, but nothing is wasted enough to derail the agent.

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?

No output schema exists, yet the description specifies the return format, error-per-item behavior, undo semantics, and how to verify results via get_element_details with matching field names. For a complex, high-parameter creation tool this is complete enough to call correctly.

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 100%, so baseline is 3, but the description adds genuine semantics beyond the schema: 'level' is relative to the home story and, with referencePlane 'Top', denotes slab top; thickness is ignored for composite slabs; and the tool default for referencePlane may differ from the passed value. These clarifications exceed what the field descriptions alone convey.

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?

States a specific verb and resource ('Creates slabs') and immediately scopes the domain (floors, ceilings, flat roofs, terraces) with the geometry input (plan polygon with arcs and holes). An agent can distinguish this from create_roofs, create_shells, or modify_slabs without opening a schema.

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?

Gives clear usage context: element types it covers, that units are meters/degrees, that unspecified settings fall back to tool defaults, and that story defaults to current unless 'storyIndex' is given. It does not, however, explicitly route the agent away from siblings (e.g., 'use create_roofs for pitched roofs'), which is the only gap.

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