start_ui

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

Annotations include readOnlyHint: true, openWorldHint: true, and idempotentHint: false. The description goes beyond these by disclosing the iterative loop (screenshot scoring), the planning phase before generation, and the acceptance criteria. This adds behavioral context: the tool may ask questions (loop), generate multiple revisions, and depend on external screenshot evaluation. No contradiction with annotations.

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 concise: one sentence that captures the three-phase workflow. It front-loads the purpose before listing any parameters. However, given the complexity (19 parameters, multi-step process), a slightly expanded description might be warranted to avoid ambiguity. Minimal waste, but could do more without bloating.

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 high parameter count (19), rich annotations (readOnly, openWorld), and no output schema, the description provides a solid high-level narrative. It explains the iterative and screenshot-based nature of the tool. However, it does not mention what happens if 'loop' mode or 'auto' mode is selected, nor the role of templates or project_root. Still, for a tool with this complexity, the description is reasonably complete.

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 description coverage is 100%, so the baseline is 3. The description does not add much parameter-level semantics beyond what the schema already provides. It mentions locking visual direction and generating pages, which loosely maps to visual_direction and description, but does not explain complex parameters like requirements_mode or loop_* in greater depth. No extra value beyond 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 the tool orchestrates UI design and development: first locking visual direction and information architecture, then generating key pages, and finally iterating with real screenshots. This is a specific verb+resource (orchestrate UI development) with a step-by-step process. It is reasonably distinguishable from sibling tools like ui_design_system (which likely focuses on design tokens) and ui_search (which is about searching).

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 implies the tool is used for starting a UI design workflow, but it does not explicitly state when to use this vs. siblings like ui_design_system or converge. There is no guidance on prerequisites (e.g., existing project root?), exclusion criteria, or alternative tools. The context is implicit but not explicit enough to help an agent decide between siblings.

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