get_selection

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

With no annotations, the description fully bears the burden of disclosure. It describes the return object structure, preconditions, and error states. It does not mention authentication details beyond connectivity, but that is acceptable for a read-only tool.

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 well-structured and front-loaded with purpose, but includes several sentences that could be slightly condensed. However, it remains efficient and informative.

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?

Despite lacking output schema, the description provides a detailed return format including optional fields (layoutMode?, padding/sizing/itemSpacing?, etc.), prerequisites, error conditions, and usage guidance. It is fully complete for a read-only selection tool.

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?

There are no parameters, so schema coverage is 100% trivially. The description adds value by detailing the output structure, which is necessary since there is no output schema.

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 it retrieves selected nodes with layout/style details, distinguishing it from siblings like capture_screenshot and analyze_design which operate on node IDs.

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?

Explicitly lists prerequisites (bridge + plugin connected), edge case (empty selection returns []), error condition (isError if not connected), and recommends usage for obtaining node IDs or reading layout/variants before writing a spec.

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