get_selection

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 the returned fields (id/name/type) and the environment constraint (Figma Desktop), which is genuinely useful, but says nothing about behavior with an empty or multi-node selection, or about connection/error requirements.

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 sentence with no filler that front-loads the return payload and then the scoping condition. Nothing could be removed without losing information.

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?

There is no output schema, so the description must cover the return value, and it only does so in outline (id/name/type) without describing shape, cardinality, or the empty-selection case. For a zero-parameter read tool this is adequate but leaves real gaps for an agent that needs to handle the no-selection state.

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?

The tool takes zero parameters, so there is no parameter semantics to explain; the baseline of 4 applies. The description correctly implies the implicit input is the live editor selection rather than a supplied argument.

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 a specific verb and resource (return id/name/type of nodes) with a clear scope qualifier: the nodes currently selected on the canvas. This separates it from get_node/get_node_tree, which take an explicit node target; the 'current selection' framing is distinctive enough that an agent won't confuse it with those siblings.

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 — the word 'сейчас' signals it reads live editor state, which is a useful contextual cue. But the description never states when to choose it over get_node or find_node, nor any prerequisite (e.g. a connected Figma Desktop plugin session).

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