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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so the safety profile is covered. The description adds real value by listing the analysis categories produced (container aggregation, CSS styles, layout inference, repeated-pattern detection, resource URLs) and reaffirming no screenshot is returned.

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?

Front-loaded with the key differentiator (JSON only, no screenshot), then output contents, Args, and Returns in a scan-friendly layout. Minor redundancy between the '输出包含' list and the 'Returns' line, but no wasted filler.

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 carries the burden of describing returns and does so adequately via the analysis categories. For a single-parameter read tool with full annotation coverage, nothing critical is missing, though it could note behavior for large/deep nodes.

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% and the schema already explains extraction from the Figma URL node-id parameter in more detail than the description. The description merely restates node_id as required, adding nothing beyond the structured field, so the baseline 3 applies.

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+resource (get structured analysis JSON for a Figma node) and explicitly excludes screenshots, which distinguishes it cleanly from figma_get_screenshot. It enumerates what the analysis contains, so an agent knows exactly what it returns without opening a schema.

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 names the condition for use — '适合在已有截图的情况下补充获取结构数据' (use when a screenshot already exists and you want supplementary structural data) — and rules out screenshot retrieval. It doesn't cite sibling tools by name, so the routing is implied rather than explicit.

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

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

Annotations already declare openWorldHint, idempotentHint, and non-destructive mutation, so the description's flow (fetch, analyze, download via localhost) provides some useful context about internal steps and authentication-like localhost URLs. However, it does not reveal what gets written, whether existing files are overwritten, or any rate limits, which are important for a non–read-only operation.

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 structured with a clear flow list and parameter/return sections, and it is front-loaded with the main action. It is slightly repetitive (e.g., repeating parameter names from schema) but overall efficient.

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 annotations covering safety hints and no output schema, the description provides the core process and return summary. However, it omits details about file overwrite behavior, error handling, permissions needed for localhost downloads, and any workspace path constraints, leaving gaps for a write operation.

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 both parameters fully. The description repeats the same parameter names with '必填' but adds no additional syntax or format details beyond what the schema provides.

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 ('分析指定节点并将所有图片/SVG 资源下载到本地目录') and clearly distinguishes it from siblings like figma_get_screenshot or figma_analyze_structure by emphasizing the download-to-local action.

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?

Usage is implied by '分析指定节点' and the download flow, but there are no explicit when-to-use/when-not-use statements or alternative tools mentioned. An agent can infer the context but is not given guidance on choosing this tool over siblings.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower. The description still adds meaningful context beyond them: it discloses the return payload composition (a directly viewable screenshot plus a semantic JSON with CSS values, text, image URLs, container hierarchy, layout direction, and repeated-pattern flags), which is genuinely useful since no output schema exists.

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 numbered list is well front-loaded and structured, and the Args/Returns sections are clean. However, the return contents are stated twice — once in the bullet list and again in the following paragraph ('精确的 CSS 值...容器层级关系...重复模式标记') — which is avoidable repetition.

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 carries the return-value burden and does so adequately, enumerating the three payload components and their key contents. The lone parameter is fully documented in both schema and description. It is nearly complete for a one-parameter composite read tool; only an explicit sibling comparison is missing.

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?

With a single parameter at 100% schema description coverage, the schema already documents node_id fully, including the '0:118' / '0-118' formats and the advice to extract it from the URL's node-id param. The description only repeats the same example IDs, adding no semantics beyond the 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?

States a specific verb+resource (get full design context for a Figma node) and enumerates exactly what that context contains — screenshot, structured semantic JSON, and asset URLs. Calling itself 'the main entry point for restoring Figma designs' gives a clear role, though it never explicitly contrasts itself with the overlapping siblings (figma_get_screenshot, figma_analyze_structure, figma_download_assets) whose functionality it appears to bundle.

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?

'This is the main entry point' is an implied usage signal that an agent would likely follow, but there is no explicit when-to-use vs. when-to-prefer-a-sibling guidance, despite three siblings covering screenshot, structure analysis, and asset download separately. Usage is inferable but not spelled out.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds the return media type (image/png) and that the payload is an image, which matters because there is no output schema, but it says nothing about size, scaling, or resolution behavior.

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?

Short and front-loaded, with purpose in the first clause. The Args/Returns blocks mostly duplicate the schema and annotation information rather than earning their space, keeping it just under top marks.

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 one-parameter read-only tool with full annotation coverage, the description covers purpose, the required input, and the return type. It lacks sibling differentiation and any note on image scaling/options, which are the only real gaps.

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% and the single parameter is fully documented in the schema, including the URL node-id extraction hint that the description omits. The description merely restates the parameter name, so baseline 3 applies.

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+resource: retrieve a screenshot of a specified Figma node, with output format (image/png) named. It does not differentiate itself from siblings such as figma_download_assets, which is the closest overlap, so it stops short of a 5.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. An agent cannot tell from the description alone why it should call this rather than figma_download_assets or figma_get_page_context.

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

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

注解已声明 readOnlyHint=true、idempotentHint=true 和安全特性。描述中增加了输出示例（token 键值对）和返回值描述，提供了一些操作结果透明度，但未说明速率限制、认证要求或开放世界行为等额外上下文。注解已覆盖安全特性，因此评分 3 是合适的。

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?

结构清晰，含示例、参数说明和返回值说明，句子均简洁。略有冗余（例如同时列出参数名和类型），但整体无冗长内容，且用途说明前置。

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?

对于无输出架构的简单单参数只读工具，描述补充了输出示例和返回值说明，足以让代理正确调用。但由于未解释变量可能不存在时的行为或服务限制，并未达到 5 分。

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?

架构描述覆盖率达 100%，因此参数已在模式中完整记录（包括从 Figma URL 提取的提示）。描述中列出了参数名和类型，但并未超出模式提供额外含义。在模式承担主要说明的情况下，3 分符合基准。

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?

明确以动词+资源开头（'获取...设计变量定义'）并提供具体示例（颜色、间距、字体）。它并未明确区分兄弟姐妹工具如 figma_get_page_context，但核心意图是清晰的。

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?

提到'适合提取设计系统 token'，给出了隐含的使用场景，但未指明何时使用或不使用此工具，也未提及替代方案（例如，获取页面上下文或截图）。

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