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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond them: the output contents, the supported languages, and the intended downstream consumption. It omits any note on rate limits, truncation, or the shape of the returned text.

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 what is returned and its intended use, then the accepted input forms. No filler and every clause carries information an agent needs to select and call the tool.

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?

With no output schema, the description must carry the return-value burden, and it largely does by enumerating the prompt contents and language options. It never says whether the result is one combined string, a per-pattern array, or how the six-pattern case is structured, which is a modest remaining gap for a no-output-schema 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning the schema does not: inputs may be ids, names, or short descriptions (fuzzy resolution), and the 1–6 bound is restated in prose with examples. It does not explain how ambiguous descriptions are resolved or what happens on a miss.

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 'ready-to-use implementation instructions for 1 to 6 UI patterns', and enumerates the payload (what to build, where it sits, states, accessibility). The framing 'for pasting into an AI coding tool such as Claude Code or Cursor' clearly separates it from sibling lookups like get_ui_pattern, list_ui_patterns and search_ui_patterns that surface pattern data rather than build instructions.

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?

Gives clear context of use — generating prompts to paste into an external AI coding tool — and implies the natural inputs (ids, names or short descriptions). It does not state when NOT to use it or explicitly route to alternatives such as get_ui_pattern for plain pattern details, so it stops short of full when/when-not guidance.

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