write_node

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

With no annotations, the description must carry the behavioral burden. It usefully discloses that the operation runs through the plugin against an already-open file and that no REST fallback exists, but it says nothing about required permissions, behavior when parentNodeId is invalid or missing, or what the call returns. The operationId idempotency semantics live only in the schema, not in the description.

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 short clauses: what it creates and where, which sibling to use instead, and why the plugin path is mandatory. Front-loaded with the primary capability, zero 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 16-parameter mutation tool with nested Auto Layout and typography objects and no annotations, the description orients the agent on node scope, sizing/styling capabilities, and the plugin requirement. The remaining gap is the return value: with no output schema, the agent is not told that a node id comes back, which it needs to chain into move_node or update_node.

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 50% across 16 parameters, so the description needs to compensate and only partly does: it names the supported styling groups (fills/strokes/cornerRadius/effects, typography, Auto Layout), which helps orient the agent among the many optional groups. It adds no meaning for parentNodeId, operationId, or strokeWeight beyond what the schema already says.

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?

States a specific verb and resource ('Создаёт ноду ... в открытом файле Figma') and enumerates the supported node types (FRAME, RECTANGLE, TEXT). It also distinguishes itself from the component-creation sibling by naming create_instance for components/instances, so an agent can route correctly without reading either 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?

Gives explicit routing guidance: use create_instance for components and instances, and it notes that Figma's REST API is read-only so the Plugin Bridge is the only path. It does not say when to prefer update_node over creating a new node, which is the nearest alternative for post-creation edits.

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