Create a multiple-choice question for a paper with customizable stem, options, correct answers, and explanations. Supports plain text, Markdown, or rich text input.
创建多选题
| Name | Required | Description | Default |
|---|---|---|---|
| paper_id | Yes | 试卷ID（通过 query_group_tasks 获取） | |
| question | Yes | ||
| need_parse | No | true 返回纯文本（plain），false 返回原始富文本结构（raw） | |
| need_detail | No | 是否在返回中包含完整题目内容（选项、答案等），仅需确认成功时设为 false |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.5.2Input schema / $defs / MultipleChoiceQuestion / properties / title / descriptionPrevious value: -"题干纯文本（与 title_raw 二选一）。只在一两行的简单题目用；结构化题干（OJ、分小节）走 title_raw。"New value: +"题干纯文本（与 title_md/title_raw 三选一）。只在一两行的简单题目用。"Input schema / $defs / MultipleChoiceQuestion / properties / title_assetsAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "additionalProperties": true,
+ "type": "object"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "题干 Markdown 引用的资源列表，仅与 title_md 一起使用。格式：[{\"id\":\"img_1\",\"type\":\"image\",\"name\":\"图.png\",\"file_path\":\"/abs/图.png\"}]；图片占位：，附件占位：[附件名](asset://file_1)。",
+ "title": "Title Assets"
+}Input schema / $defs / MultipleChoiceQuestion / properties / title_mdAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "题干 Markdown（与 title/title_raw 三选一）。工具会自动转为小雅 Draft.js 富文本；适合 AI 输出的分节题干、列表、代码块、样例输入输出；图片/附件用 asset://id 占位并配合 title_assets。",
+ "title": "Title Md"
+}Input schema / $defs / MultipleChoiceQuestion / properties / title_raw / descriptionPrevious value: -"题干富文本（Draft.js 格式），与 title 二选一，优先本字段。\n格式：{\"blocks\": [...], \"entityMap\": {}}，每行一个 block，空行 = text=\"\" 的 unstyled block。\nblock.type 常用：unstyled / header-one~six / code-block / ordered-list-item / unordered-list-item / blockquote。\ninlineStyleRanges.style 常用：BOLD / ITALIC / UNDERLINE / CODE / lineThrough / color-red / backgroundColor-#ffff02 / fontSize-20。\noffset/length 以 UTF-16 单位计数（中文一字 1 单位）。\n美化要点：小标题【XX】整段 BOLD、小节间留空行、样例用 code-block、关键词用 CODE 或 color-blue；\n完整支持矩阵见 xiaoya-teacher-skill/references/title_rich_text.md。"New value: +"题干富文本（Draft.js 格式），与 title/title_md 三选一，优先本字段。\n格式：{\"blocks\": [...], \"entityMap\": {}}，每行一个 block，空行 = text=\"\" 的 unstyled block。\nblock.type 常用：unstyled / header-one~six / code-block / ordered-list-item / unordered-list-item / blockquote。\ninlineStyleRanges.style 常用：BOLD / ITALIC / UNDERLINE / CODE / lineThrough / color-red / backgroundColor-#ffff02 / fontSize-20。\noffset/length 以 UTF-16 单位计数（中文一字 1 单位）。\n美化要点：小标题【XX】整段 BOLD、小节间留空行、样例用 code-block、关键词用 CODE 或 color-blue；\n完整支持矩阵见 xiaoya-teacher-skill/references/title_rich_text.md。"Input schema / $defs / QuestionOption / properties / text / descriptionPrevious value: -"选项纯文本，与 text_raw 二选一"New value: +"选项纯文本，与 text_md/text_raw 三选一"Input schema / $defs / QuestionOption / properties / text_assetsAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "additionalProperties": true,
+ "type": "object"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "选项 Markdown 引用的资源列表，仅与 text_md 一起使用，格式同 title_assets",
+ "title": "Text Assets"
+}Input schema / $defs / QuestionOption / properties / text_mdAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "选项 Markdown，与 text/text_raw 三选一，工具会自动转为小雅 Draft.js 富文本；图片/附件用 asset://id 占位并配合 text_assets。",
+ "title": "Text Md"
+}Input schema / $defs / QuestionOption / properties / text_raw / descriptionPrevious value: -"选项富文本，与 text 二选一"New value: +"选项富文本，与 text/text_md 三选一"v1.3.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavioral traits. The description '创建多选题' provides no information about side effects, return values, permissions, or any other behavioral aspects.
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 extremely concise (one phrase) but lacks any structure or useful content. It fails to provide value beyond the tool name, making it under-specified rather than efficiently concise.
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 complexity of the input schema with nested objects and many options, the description is woefully incomplete. It does not explain the creation process, return values, or how to use the parameters, leaving the agent with insufficient context.
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 75%, meaning the schema already describes most parameters. The description adds no new meaning beyond the schema, as it only states the tool's function. The schema's parameter descriptions are detailed, so the description does not need to compensate.
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 '创建多选题' translates to 'Create multiple choice question', which states the verb and resource but lacks specificity to distinguish it from sibling tools like create_single_choice_question or create_true_false_question. The purpose is clear but minimal.
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?
No usage guidelines are provided. The description does not indicate when to use this tool over alternatives, nor does it mention any prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Sav1ouR520/xiaoya-teacher-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server