set_properties

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

No annotations are supplied, so the description carries the full behavioral burden for a mutation tool, and it delivers very little. It does not say whether unlisted properties are preserved, whether changes are reversible/undoable, what happens if the id is invalid, or how the free-form props object is interpreted. The bare verb 'Ubah' is the only behavioral signal, which is insufficient for an unannotated write operation.

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?

A single, front-loaded sentence with the resource and the property inventory stated immediately; no filler or redundancy. It could be tightened only slightly by adding a usage clause rather than by removing anything.

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 an unannotated mutation tool whose core parameter is an undifferentiated free-form object and with no output schema, the description is materially incomplete. The agent is left without the props key vocabulary, the return/confirmation shape, or failure behavior — all of which the structured fields fail to supply here. The property-family list is a start but does not close the gap.

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 nominally 100%, but the two schema descriptions are near-tautological ('ID layer yang akan diubah', 'Properti yang diubah'), and props is declared as a free-form object with additionalProperties: {} and no key documentation at all. The description partially compensates by listing the property categories that belong in props (fills, stroke, typography, corner radius, corner smoothing, effects, auto-layout), which is genuinely additive. However it gives no key names or value formats, so the agent still cannot construct props reliably — above baseline but well short of adequate.

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 (Ubah/change) and resource (visual properties on an existing canvas node) and enumerates the property families covered: fills, stroke, typography, corner radius, corner smoothing, effects, auto-layout. The phrase 'pada node yang ada di kanvas' implicitly separates it from creation siblings like create_node. It stops short of naming an explicit alternative, so it is clear but not sibling-differentiating at the level 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?

Usage is only implied: 'node yang ada di kanvas' signals this applies to existing nodes rather than new ones, which is a useful implicit boundary against create_node. There is no explicit statement of when to prefer this over figcraft_batch (for multiple nodes) or other sibling tools, and no prerequisites are given. This is minimum-viable guidance rather than routing guidance.

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