get_selection

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

The description states this is a read-like operation, but annotations have destructiveHint=true, which is contradictory. The description does not clarify why it might be destructive or disclose any side effects. With no additional behavioral context beyond the contradiction, the score is 1.

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?

The description is two sentences: the first states the core function and return behavior, the second provides usage guidance with alternatives. Every word serves a purpose, and it is front-loaded with the main action.

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?

Given the contradiction with annotations, the description fails to provide complete context about the tool's behavior. It does not explain the destructive nature implied by annotations, nor does it specify the format of returned nodes. For a simple tool, it should clarify the discrepancy.

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 has no parameters, and schema coverage is 100%. As per the rubric, 0 parameters gives a baseline of 4. The description does not need to add parameter semantics since there are none.

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 clearly states the verb 'Get' and the resource 'nodes currently selected in Figma'. It also specifies the return behavior (empty array if nothing selected) and distinguishes from siblings by mentioning get_design_context and get_node for deeper detail.

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 explicitly says when to use this tool (to get the current selection) and when not to (use get_design_context or get_node for deeper detail on a specific node). It provides clear alternatives.

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