Inspect Design Images

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries real additional weight: no vision/drawing model is invoked, no web pages are fetched, inputs pass format/size/public-URL validation, and the result is delivered as MCP image content. It stops short of describing failure behavior (e.g., what happens when one of several URLs fails validation) or rate/size limits beyond 'along existing checks'.

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 core capability, input forms, and Host obligations are front-loaded and every sentence carries information. It is dense to the point of being packed, with the Host-behavior constraints bundled into the same block as input rules rather than separated.

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?

An output schema exists, so return shape need not be explained; the description still covers input source rules, validation, what is transmitted to the Host, and what the Host may and may not conclude. Nothing essential for correct invocation is missing for a one-parameter read 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 0% for the single `images` array, so the description must compensate, and it does: it defines the accepted value forms (absolute local path or public image URL), the count bounds (1–4), and that each entry is validated. It does not mention the 4096-character-per-item limit or whether mixed local/URL arrays are allowed, so it is not fully compensating.

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 states a specific verb and resource ('免费读取1–4张产品图/对标图') and the output channel ('以MCP图片内容交给Host观察'), and explicitly scopes out what the tool does not do ('不调用视觉或绘图模型'). This cleanly separates it from the surrounding generation/task siblings (generate_images, submit_image_tasks, inspect-style reads).

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?

It defines accepted inputs (本机绝对路径或公开图片直链) and rules them out ('不抓网页'), plus post-processing expectations for the Host (record appearance, color, proportion, layout; do not infer performance params or copy competitor facts). What it lacks is an explicit comparison to the sibling tools — no statement of when to call inspect_design_images rather than plan_ecommerce_design or build_reference_replica_prompts.

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