Create skylights

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive mutation. The description adds value beyond them: "(one undo step)" discloses undo granularity, and the "[{guid, type} | {error}] in input order" clause reveals partial-failure semantics and per-item result ordering. It stops short of describing rollback behavior when some items fail.

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?

Three tight sentences, front-loaded with purpose before prerequisites and return format. Every clause carries information (undo scope, required fields, defaulting, localization, result shape) with no filler.

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?

For a highly complex tool with a very rich nested schema and no output schema, the description covers the essentials: required fields, defaulting behavior, the localization caveat, and the return shape with error signaling. It could say more about how partial failures affect the whole batch, but nothing critical for invocation is missing.

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?

Top-level schema description coverage is 0% (the single 'skylights' array is undocumented), so the description carries real weight here: it explains that size, library part, and parameters fall back to the Skylight tool settings by default, and flags that library part names are LOCALIZED — a genuine gotcha not stated at the top level. It does not enumerate the many optional per-item fields, which the nested schema documents well.

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 names a specific verb and resource ("Places skylights into roofs or shells") and implicitly distinguishes this from siblings like create_roofs, create_shells, and create_openings by naming the host requirement. An agent can tell what this tool produces without opening the 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?

It states the invocation prerequisites clearly (each skylight needs 'owner' as a Roof/Shell GUID and 'point' as a plan position), and routes the agent to search_library_parts for localized part names. There is no explicit when-not-to-use guidance or comparison against related creation tools, but the context is unambiguous.

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