inspect_ui

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It reveals the model used (MiMo-V2.5), that the output is structured design data rather than literary prose, the exact 13 result categories, and the timing for proactive invocation. It stops short of stating return format details (e.g., whether output is JSON or a document) or any side effects/auth needs, but given that the tool is a vision analysis over local image paths, the disclosed behavior is adequately transparent for an AI agent.

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 substantial but well-structured: it leads with the model and purpose, then a compact list of the 13 return items, then a clear '主动调用时机' paragraph, and finally parameter guidance. Each sentence earns its place, though the 13-item enumeration is somewhat long. Front-loading is effective: the first sentence immediately tells the agent what the tool does and for whom.

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 tool with no annotations and no output schema, the description does a solid job: it explains the output structure (13 named items), gives concrete trigger phrases, and clarifies parameter roles. It doesn't specify the exact output format (JSON vs. text) or how errors are handled, which are minor gaps. Given the tool's moderate complexity (mutually exclusive parameters, optional context, multi-image support), the description is sufficiently complete for an agent to invoke it correctly in most scenarios.

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 structured schema already documents all four parameters thoroughly, including file path examples and supported formats. The description adds value beyond the schema by explaining the conceptual roles of the parameters: '多图时逐个说明角色与差异' for image_paths, 'task 说明目标' with examples, and 'project_context 可选，提供技术栈等背景'. This semantic framing helps the agent map user intent to the correct parameter values.

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 opens with a specific verb ('用 MiMo-V2.5 视觉模型对 UI 截图做工程化分析') and clearly identifies the resource (UI screenshots) and purpose (replicating/modifying frontend for Coding Agents). It distinguishes itself from generic image analysis by emphasizing structured design data, listing the 13 return items, and stating when to proactively call it (e.g., user asks to '复刻这个页面' or '按截图/设计图改前端'). This separates it from siblings like analyze_image or compare_images.

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 includes a dedicated '主动调用时机' section that explicitly states when to use this tool ('用户要复刻这个页面', '按截图/设计图改前端', '根据参考图实现 UI'). It also clarifies that task describes the goal and project_context is optional, and the image_path/image_paths mutual exclusivity guides selection. Although it does not name sibling alternatives explicitly to exclude, the trigger conditions are concrete and distinct enough to prevent confusion with analyze_image/compare_images.

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