Skip to main content
Glama

google_scholar

Destructive

当用户需要查询 Google Scholar 学术论文、作者、引用、出版物或学术搜索结果时触发。

Input Schema

NameRequiredDescriptionDefault
qYes该参数定义您想要搜索的查询内容。调用方必须提供非空值,不使用默认值。
hlNo该参数定义 Google 职位搜索要使用的语言。它是一个两位数的语言代码,例如 en 代表英语,es 代表西班牙语,fr 代表法语。
lrNo该参数定义一个或多个将搜索限制在的语言。它使用 lang_{两位语言代码} 指定语言,并使用 | 作为分隔符,例如 lang_fr|lang_de 将仅搜索法语和德语的页面。
numNo该参数定义返回的最大结果数量,范围为 1 到 20,默认为 10。10
jsonNo该参数定义采集结果的输出格式。可选择 JSON、HTML(支持下载)格式,默认为 JSON;1 返回 JSON,2 返回 JSON+HTML,3 返回 HTML,4 返回 Light JSON。1
safeNo该参数定义成人内容的过滤级别。可以设置为 active 或 off,默认情况下 Google 会模糊处理露骨内容。
as_rrNo该参数定义是否仅显示综述文章(这些文章包括主题综述,或讨论您搜索的作品或作者)。可以设置为 1 以启用此过滤器,或设置为 0(默认)以显示所有结果。0
citesNo该参数定义用于触发“被引”搜索的文章唯一 ID。使用 cites 将显示 Google 学术中引用该文献的列表。示例值:cites=1275980731835430123。cites 和 q 参数同时使用会触发在引用文献中的搜索。
startNo该参数定义结果偏移量。它跳过指定数量的结果,用于分页。例如 0(默认)是第一页结果,10 是第二页结果,20 是第三页结果,依此类推。0
as_sdtNo该参数既可用作搜索类型,也可用作过滤器。作为过滤器(仅在搜索文章时有效):0 排除专利(默认),7 包含专利。作为搜索类型:4 选择判例法(仅限美国法院)。0
as_visNo该参数定义是否希望包含引用。可以设置为 1 以排除这些结果,或设置为 0(默认)以包含它们。0
as_yhiNo该参数定义您希望包含结果的结束年份。例如将 as_yhi 设置为 2018 年,则该年份之后的结果将被省略。此参数可与 as_ylo 参数结合使用。
as_yloNo该参数定义您希望包含结果的起始年份。例如将 as_ylo 设置为 2018 年,则该年份之前的结果将被省略。此参数可与 as_yhi 参数结合使用。
filterNo该参数定义“类似结果”和“省略结果”的过滤器是开启还是关闭。可以设置为 1(默认)以启用这些过滤器,或设置为 0 以禁用这些过滤器。1
scisbdNo该参数定义过去一年添加的文献,按日期排序。可设置为 1 以仅包含摘要,或设置为 2 以包含全部内容。默认值为 0,表示文献按相关性排序。0
clusterNo该参数定义用于触发“所有版本”搜索的文章唯一 ID。示例值:cluster=1275980731835430123。禁止将 cluster 与 q 和 cites 参数一起使用。请仅使用 cluster 参数。
no_cacheNo默认情况下,5 分钟内缓存相同参数的搜索结果。将 no_cache 设为 true 可跳过缓存,设为 false(默认)则使用缓存结果。缓存搜索免费,且不计入搜索统计。false

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.9/5.0
Behavior1/5

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

The description frames this purely as a query ('查询') operation, i.e. a read of academic results, while the annotations declare readOnlyHint=false and destructiveHint=true. That is a direct inconsistency in the observable behavior an agent would expect, and the description adds no behavioral context (caching via no_cache, rate limits, scraping semantics) to offset it.

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

Conciseness4/5

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

A single, front-loaded trigger sentence with no filler, which is efficient. Its brevity is the main limitation for such a complex tool rather than verbosity, but structurally it is clean and wastes nothing.

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?

For a 17-parameter tool with no output schema, the description never explains return format/volume, pagination expectations despite start/num existing, or the interaction of mutually exclusive params (cluster vs q+cites). One trigger sentence is too thin to be complete for this complexity.

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

Parameters3/5

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

Schema description coverage is 100%, so all 17 parameters (q, hl, lr, num, cites, cluster, start, etc.) are already fully documented in the schema. The description adds no parameter-level meaning beyond what the schema provides, so the baseline of 3 applies.

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 names a specific resource (Google Scholar) and its queryable entities (academic papers, authors, citations, publications, search results), so an agent can tell it targets scholarly search rather than general web search. It does not explicitly differentiate from siblings like google_search or google_patents, but the resource is unambiguous.

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

Usage Guidelines3/5

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

It gives a trigger condition ('当用户需要查询 Google Scholar 学术论文…时触发'), which implies when to use it. However, it offers no exclusions or named alternatives (e.g. use google_search for general pages, google_patents for patents), leaving the agent to infer routing decisions.

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