vw2d_setup

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

Annotations already declare non-read-only, non-destructive, closed-world, so safety is covered. The description adds real semantics beyond that: existing classes keep their name and given attributes are applied (a merge, not a replace), and the template is gated on document state and user consent. It still omits what happens to attributes not supplied and whether layers are likewise merged or replaced.

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?

Purpose is front-loaded, and the JSON-shaped examples earn their space because the schema itself is opaque. Density is high with no filler sentences, though the inline example formatting is a bit hard to parse and the attribute list could be structured more scannably.

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 5-parameter mutation tool with no output schema, the description covers the two substantive parameters in depth, states the merge behavior for existing classes, and constrains the template. Missing pieces are the two active_* parameters and any statement of what is returned or how failures (e.g. unknown layer) are reported.

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 0% and every array item is an untyped object with additionalProperties:true, so the description is doing heavy lifting: it spells out the class attribute keys (pen, fill, hatch, line_weight in mm, line_style, opacity), the '-' hierarchy convention, and the layer shape ({name, scale}). The gap is active_class and active_layer, which appear nowhere in the description and are unguessable from the schema.

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 opening sentence states a specific verb pair and resource: create or update classes and design layers, and ties it to the outcome (organised drawings). This clearly separates it from read-side siblings like vw_list_classes / vw_list_layers. It does not explicitly distinguish itself from vw2d_set_attributes, which also touches class attributes, so it falls short of a 5.

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?

There is one genuine conditional guideline: use template "architektur" only if the document has no class standard yet and the user agrees — that is real when/when-not guidance. However, nothing tells the agent when to call this versus vw2d_set_attributes, vw_list_classes, or vw2d_structure, and no prerequisite (e.g. inspect existing classes first) is stated. Usage is mostly implied by the field examples.

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