Create windows

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

Annotations already declare readOnly=false, destructive=false, and idempotent=false, but the description adds substantial behavior beyond them: the batch is a single undo step, unspecified settings inherit Window tool defaults, library part names are localized, polygonal walls are rejected, and the return shape is '[{guid, type} | {error}] in input order'. This is rich operational context an agent needs before invoking.

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?

Despite covering a complex tool, every sentence carries non-redundant information: purpose/undo, placement requirements, default inheritance, localization warning, host limitation, and return format. Purpose and required inputs are front-loaded, with secondary caveats following in a logical order.

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?

There is no output schema, yet the description fully documents the return shape and error cases, and points to get_element_details for inspecting created windows. For a tool with a deeply nested item schema, it covers the cross-cutting concerns (defaults, localization, host restrictions, undo grouping) that the schema cannot express.

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?

With schema description coverage reported at 0%, the description must compensate, and it does for the core semantics: it explains the required host wall GUID, the position-vs-point alternative and their coordinate meanings, sillHeight's reference ('bottom of the window above the wall bottom'), and which fields fall back to tool defaults. It does not restate every schema-level parameter, but it covers the high-risk ones that determine correct invocation.

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 opens with a specific verb+resource: 'Places windows into walls', immediately distinguishing it from sibling creation tools such as create_doors, create_openings, and create_walls. It also scopes the operation ('one undo step'), so an agent knows exactly what this tool produces.

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 prerequisites clearly (host wall GUID plus either 'position' or 'point'), names the host limitation ('Polygonal walls cannot host windows'), and routes the agent to search_library_parts for localized names and get_element_details for inspection. It stops short of explicitly naming alternative tools and when to prefer them, so it is clear context rather than full routing guidance.

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