Skip to main content
Glama

奇妙生产力 · Qimiao Productivity

search_templates

Read-onlyIdempotent

免费检索实际模板。PPT可直接传完整需求(中英文)和可选constraints;服务端按多页视觉档案、背景明暗、用途、风格和排除条件返回最多五套推荐。结合evidence_previews展示封面与正文、fit和review的实际复核范围;不足五套不凑数,无匹配先调整需求。用户未选采用default_selection;报价将其template_id、template_version及存在时的template_internal_version放入input固定选择。检索不制作PPT、不生成图片、不收费。小红书封面支持完整自然语言要求,以及form、purpose、mood、color、brightness、photos、title、include_subjects、exclude_subjects等筛选;展示最多五张实际预览、推荐理由和素材提示,让用户选择后用template_id和template_version固定。不要把来源网站的使用量称为小红书爆款证据。AI前端网页设计使用ai-web-design,query最多2000字,所有用途、风格和排除条件写入自然语言query;返回设计分析及最多五套模板预览和Demo。必须让用户选定并认可后,再用template_id和template_version固定轻量编辑报价;交付前端源码供二次修改,不承诺完整网站开发或部署。其他工具仅在get_tool声明templates=true时调用。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tool_id": "<tool_id>"
    },
    "name": "search_templates"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryNo
offsetNo
tool_idYes
constraintsNo

Output Schema

NameRequiredDescriptionDefault
recoveryYes
next_stepYes
schema_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / constraints / properties / exclude_subjects
      Added value: +{
      +  "items": {
      +    "enum": [
      +      "person",
      +      "product",
      +      "animal",
      +      "landscape",
      +      "food",
      +      "interface",
      +      "illustration",
      +      "none"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 8,
      +  "type": "array"
      +}
    • addedInput schema / properties / constraints / properties / form
      Added value: +{
      +  "enum": [
      +    "big-type",
      +    "memo",
      +    "notebook",
      +    "illustration",
      +    "photo-title",
      +    "collage",
      +    "dialog",
      +    "comparison",
      +    "magazine",
      +    "product",
      +    "infographic"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / constraints / properties / ignored
      Added value: +{
      +  "items": {
      +    "maxLength": 80,
      +    "pattern": "^(?:color|form|purpose|mood|topic|brightness|photos|photo|subjects|required_subjects|exclude_color|exclude_mood)(?::[a-z][a-z-]{0,35})?$",
      +    "type": "string"
      +  },
      +  "maxItems": 20,
      +  "type": "array"
      +}
    • addedInput schema / properties / constraints / properties / include_subjects
      Added value: +{
      +  "items": {
      +    "enum": [
      +      "person",
      +      "product",
      +      "animal",
      +      "landscape",
      +      "food",
      +      "interface",
      +      "illustration",
      +      "none"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 8,
      +  "type": "array"
      +}
    • addedInput schema / properties / constraints / properties / mood
      Added value: +{
      +  "enum": [
      +    "professional",
      +    "minimal",
      +    "playful",
      +    "gentle",
      +    "retro",
      +    "cute",
      +    "bold",
      +    "editorial"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / constraints / properties / photos
      Added value: +{
      +  "enum": [
      +    "none",
      +    "available",
      +    "any"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / constraints / properties / purpose / enum
      Previous value: -[
      -  "report",
      -  "technical",
      -  "product",
      -  "education",
      -  "research",
      -  "marketing",
      -  "culture",
      -  "event"
      -]New value: +[
      +  "report",
      +  "technical",
      +  "product",
      +  "education",
      +  "research",
      +  "marketing",
      +  "culture",
      +  "event",
      +  "tutorial",
      +  "list",
      +  "comparison",
      +  "review",
      +  "guide",
      +  "experience",
      +  "emotion",
      +  "quote"
      +]
    • addedInput schema / properties / constraints / properties / title
      Added value: +{
      +  "maxLength": 300,
      +  "type": "string"
      +}
    • addedInput schema / properties / constraints / properties / topic
      Added value: +{
      +  "enum": [
      +    "technology",
      +    "career",
      +    "education",
      +    "travel",
      +    "food",
      +    "beauty",
      +    "home",
      +    "parenting",
      +    "health",
      +    "fitness",
      +    "pet",
      +    "lifestyle",
      +    "business",
      +    "generic"
      +  ],
      +  "type": "string"
      +}
  2. First observed

TDQS

A3.5/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses free search, a maximum of five results, no padded results when fewer than five match, evidence previews, and the expectation to adjust requirements when nothing matches. These are substantive behavioral details that help an agent set expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long and rambling, mixing PPT templates, 小红书 covers, AI web design, quote workflow, and unrelated warnings in one block. Only the first sentence is clearly front-loaded; the rest is poorly structured and repetitive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema and annotations cover return values and safety, but for a nested five-parameter search tool the description leaves key inputs unexplained and creates ambiguity about which tool some limits and constraints apply to. It does not provide enough complete guidance for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description only partially compensates by listing some constraint filters and a natural-language query. It does not explain tool_id, limit, offset, or many nested constraints, and the 'query最多2000字' note appears to refer to ai-web-design rather than this tool's 16000-character schema limit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states '免费检索实际模板' and explains it returns up to five template recommendations, which is a clear verb and resource. However, it mixes PPT, 小红书 and AI web-design routing without directly distinguishing this tool from the sibling search_tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly routes AI front-end web design to ai-web-design and says search_templates does not make PPT, generate images, or charge. It also gives workflow conditions such as requiring user selection before quote, though these are scattered rather than presented as concise when/when-not rules.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources