set_variable_binding

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. It discloses one genuinely important trait — the binding stays live across mode changes, unlike a value copy — which is exactly the kind of context annotations could not provide. It does not say what happens on an invalid field, whether the node or variable must already exist, what permissions or plugin state are needed, or what the call returns.

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?

Two sentences, front-loaded with the core semantic distinction before the per-field instructions. Every clause earns its place and there is no filler. The Russian phrasing is compact and the split between fills/strokes and other fields is easy to scan.

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 mutation tool with no annotations and no output schema, the definition covers the essential mechanics: what a binding is, and how to target the field. It leaves gaps around failure modes, existence requirements, and how the binding result is reported back to the caller. Given only four parameters and half schema documentation, an agent could call this correctly but would be guessing about edge cases.

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 50%: field and paintIndex are documented in the schema, while nodeId and variableId are bare strings. The description reinforces the field/paintIndex relationship and states the default of 0 for paintIndex, which adds a little meaning beyond the schema. It adds nothing for nodeId or variableId, so the 50% coverage gap is only partially compensated.

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 states a specific verb and resource ('Привязывает Figma variable к свойству ноды') and adds a key distinction: it binds a live variable rather than copying the current value. That is a sharp, non-tautological statement of purpose. It stops short of naming the sibling set_variable, which is the tool an agent would most plausibly confuse it with, so a 4 rather than 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?

The description gives conditional guidance for choosing between fills/strokes (use paintIndex) and other fields (just field), which is real routing information. However, that guidance is about parameter selection, not about when to use this tool versus alternatives such as set_variable or update_node. No prerequisites or exclusions are mentioned, so usage is implied rather than spelled out.

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