KRDS 페이지 뼈대

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

With no annotations, the description carries the behavioral burden and does disclose key traits: output differs drastically with vs without pattern, pattern templates come with accessibility corrections already applied, and missing required slots produce guidance rather than content. It does not state side-effect/idempotency profile or the exact return shape, but for a read-only generator the disclosed behavior is substantive.

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?

Four short sentences, front-loaded with the core behavior and then the mandatory rules. Every sentence carries a distinct instruction (what it returns, pattern vs no pattern, ordering vs component lookup, compliance rule); no 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 13-parameter, nested-object tool with no output schema and no annotations, the description covers purpose, mode selection, and sequencing well. The remaining gap is the concrete return form (HTML string vs parts vs file, and how much the caller must post-process) — the `output` parameter implies it, but the description never states it directly.

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 100%, so the baseline is 3; the description earns above baseline by giving 'pattern' real semantic weight — that it switches the tool into official-template mode with accessibility fixes and is mandatory for standard screens. The other dozen parameters (withSiteChrome, siteMenu, slots, output, etc.) are left entirely to the schema, which is adequate given full coverage.

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 (returns the starting skeleton of a KRDS page) and immediately distinguishes the two output modes: pattern specified yields a complete accessible template, omitted yields an empty skeleton. It also positions itself relative to siblings by telling the agent to call it before component lookup, so an agent can tell it apart from get_component/list_components.

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?

Explicit sequencing (call before component lookup when building a new page) and an explicit when-not/alternative path (do not hand-craft layouts; use pattern for standard login/apply screens). Both the trigger and the prohibited behavior are stated, leaving nothing to inference.

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