预览美化方案

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

With no annotations, the description carries the full behavioral burden and discloses key traits: it does not write back to Notion, the images are approximate layout/color renders rather than pixel-level screenshots, and the tool does not call a model. It leaves some operational details unstated, such as how the preview result is handed to apply_plan, but the main side-effect and output limitations are covered.

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 purpose and apply decision are front-loaded, but the description then expands into broader MCP pipeline responsibilities and repeated Fail rules that are not specific to invoking preview_page. These sentences add workflow context but dilute conciseness.

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?

There is no output schema, so the description usefully explains that the return includes before/after comparison images and estimated score changes. It also covers the key no-write and approximate-render behavior, though it does not specify how the preview output is passed to apply_plan.

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 schema already documents all four parameters including pageId, themeId, allowRecreate, and includeDestructive. The description does not add parameter-level meaning beyond that, so the baseline of 3 is appropriate.

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: it generates a beautification plan and returns before/after comparison images plus estimated score changes. It explicitly distinguishes itself from apply_plan by saying it does not write back to Notion and that the caller should decide whether to apply after viewing the preview.

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 gives clear usage timing: view the comparison first, then decide whether to run apply. It also states when not to use it, namely before content has passed review, reinforced by '内容未过关就美化 = Fail' and '只有 gate.pass 为 true 才 bloom'.

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