shape_arrayRepeat a drawing node in linear steps or rotate copies around a z-axis point to create polar arrays for fire-simulation geometry in Shape Studio.
Shape Studio: repeat a node. linear: step=[dx,dy,dz] per copy. polar: rotate copies around a z-parallel axis at axis_point=[x,y], total angle_deg (default 360).
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | ||
| name | No | ||
| step | No | ||
| count | Yes | ||
| input | Yes | ||
| angle_deg | No | ||
| axis_point | No |
Changes observed during successful MCP inspections.
v4.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the safety profile (not read-only, non-destructive, not idempotent), so the bar is lower. The description adds the geometry semantics of what happens to each copy, but says nothing about the resulting document/node-tree effects (are copies new nodes, is the source retained, naming).
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?
Front-loaded with the tool's identity, then mode-conditional details in a compact colon-delimited form; no sentence is wasted. It is close to over-terse in places ('step=[dx,dy,dz] per copy'), but structure serves the reader well.
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 7-parameter tool with zero schema description coverage and no output schema, the description should at minimum cover the required inputs. It explains the geometry transforms but omits input, count, and name entirely, so an agent cannot fully drive the tool from the definition alone.
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 0%, so the description must carry parameter meaning, and it does give real value for four of seven params: step format [dx,dy,dz], axis_point as [x,y], the 360 default for angle_deg, and the two mode values. However, two required parameters (input and count) are documented nowhere, leaving a meaningful gap.
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?
Names the operation precisely ('repeat a node') and the two pattern types (linear, polar) it produces, so an agent understands it is an array/patterning tool rather than a one-off add. It does not explicitly distinguish itself from nearby siblings like shape_mirror or shape_transform, which keeps it out of 5 territory.
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?
Usage is implied through the mode descriptions: pick linear when you want offset copies, polar when you want rotational copies. There is no explicit when-to-use statement and no routing to alternatives such as shape_mirror or shape_transform, so the agent must infer tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.