glean-tools-guide

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Glean Tools Selection Guide

Glean工具选择指南

This skill provides guidance on selecting and using Glean MCP tools effectively.

本技能为有效选择和使用Glean MCP工具提供指导。

Skills vs Agents vs Commands

Skills、Agents与Commands对比

This plugin uses three component types:

Skills (like this one): Auto-triggered guidance that helps Claude select the right tools
Agents (e.g.,
```
enterprise-searcher
```
): Autonomous workers spawned for complex multi-step tasks
Commands (e.g.,
```
/glean-search:search
```
): User-triggered structured workflows

Skills provide knowledge; agents do work; commands orchestrate workflows.

本插件使用三种组件类型：

Skills（如本技能）：自动触发的指南，帮助Claude选择合适的工具
Agents（例如
```
enterprise-searcher
```
）：为复杂多步骤任务而生的自主工作单元
Commands（例如
```
/glean-search:search
```
）：用户触发的结构化工作流

Skills提供知识；Agents执行任务；Commands编排工作流。

Tool Naming Convention

工具命名规范

Glean MCP tools follow the pattern:

mcp__glean_[server-name]__[tool]

Where

[server-name]

is dynamic and configured per user (e.g.,

default

production

acme

). The tool suffix is always consistent. When invoking tools, use whatever Glean server is available in your tool list.

Glean MCP工具遵循以下命名模式：

mcp__glean_[server-name]__[tool]

其中

[server-name]

是动态的，会根据用户配置而变化（例如

default

、

production

、

acme

）。工具后缀始终保持一致。调用工具时，请使用工具列表中可用的任意Glean服务器。

Available Tools Overview

可用工具概览

Tool Suffix	Purpose	Use When
`search`	Document discovery	Finding docs, wikis, policies, specs
`employee_search`	People lookup	Finding people, org chart, teams
`meeting_lookup`	Meeting search	Finding meetings, transcripts, decisions
`gmail_search`	Email search	Finding emails, attachments
`code_search`	Code discovery	Finding internal code, commits
`user_activity`	Activity feed	Finding your recent actions and interactions
`read_document`	Full content	Reading complete document by URL
`chat`	AI synthesis	Complex analysis across sources

工具后缀	用途	使用场景
`search`	文档查找	查找文档、维基、政策、规范
`employee_search`	人员查询	查找人员、组织架构、团队
`meeting_lookup`	会议搜索	查找会议、会议记录、决策内容
`gmail_search`	邮件搜索	查找邮件、附件
`code_search`	代码查找	查找内部代码、提交记录
`user_activity`	活动流	查找你近期的操作和交互记录
`read_document`	完整内容读取	通过URL读取文档完整内容
`chat`	AI综合分析	跨来源的复杂分析

Tool Selection Decision Tree

工具选择决策树

User question about...
├── People, "who", org chart → employee_search
├── Meetings, decisions, action items → meeting_lookup
├── Emails, attachments → gmail_search
├── Internal code, commits → code_search
├── "My activity", "what have I done", recent actions → user_activity
├── Documents, policies, specs → search
├── Need full document content → read_document (with URL)
└── Complex multi-source analysis → chat

用户问题涉及...
├── 人员、"谁"、组织架构 → employee_search
├── 会议、决策、行动项 → meeting_lookup
├── 邮件、附件 → gmail_search
├── 内部代码、提交记录 → code_search
├── "我的活动"、"我做过什么"、近期操作 → user_activity
├── 文档、政策、规范 → search
├── 需要文档完整内容 → read_document（需提供URL）
└── 跨多来源的复杂分析 → chat

Critical Rules

关键规则

1. Never Use Regular Search for People

1. 切勿使用常规搜索查找人员

undefined

undefined

WRONG

错误示例

search "John Smith"

CORRECT

正确示例

employee_search "John Smith"

undefined

employee_search "John Smith"

undefined

2. Search → Read Workflow

2. 搜索→读取工作流

When users need document details:

First:
```
search
```
to find documents
Then:
```
read_document
```
with URL from results

当用户需要文档详情时：

第一步：使用
```
search
```
查找文档
第二步：使用
```
read_document
```
并传入搜索结果中的URL

3. Use Chat for Synthesis

3. 使用Chat进行综合分析

When the question requires reasoning across multiple sources:

chat "What are our authentication best practices based on recent RFCs and security policies?"

当问题需要跨多个来源进行推理时：

chat "根据近期RFC和安全政策，我们的身份验证最佳实践是什么？"

Query Filter Reference

查询过滤器参考

Document Search (search) - Structured Parameters

文档搜索（search）- 结构化参数

The

search

tool uses separate parameters (not inline query filters):

Parameter	Type	Description
`query`	string	Keywords to find documents (required)
`owner`	string	Filter by document creator ( `"person name"` , `"me"` , `"myteam"` )
`from`	string	Filter by who updated/commented/created ( `"person name"` , `"me"` , `"myteam"` )
`updated`	string	Filter by update date ( `today` , `yesterday` , `past_week` , `past_2_weeks` , `past_month` , or month name)
`after`	string	Documents created after date ( `YYYY-MM-DD` format, no future dates)
`before`	string	Documents created before date ( `YYYY-MM-DD` format)
`app`	enum	Filter by datasource (e.g., `confluence` , `github` , `gdrive` , `slack` , `jira` , `notion` )
`type`	enum	Filter by type: `pull` , `spreadsheet` , `slides` , `email` , `direct message` , `folder`
`channel`	string	Filter by Slack channel name
`exhaustive`	boolean	Return all matching results (use for "all", "each", "every" requests)
`sort_by_recency`	boolean	Sort by newest first (only when user wants "latest" or "most recent")

search

工具使用独立参数（而非内联查询过滤器）：

参数	类型	说明
`query`	字符串	用于查找文档的关键词（必填）
`owner`	字符串	按文档创建者过滤（支持 `"人员姓名"` 、 `"me"` 、 `"myteam"` ）
`from`	字符串	按更新/评论/创建者过滤（支持 `"人员姓名"` 、 `"me"` 、 `"myteam"` ）
`updated`	字符串	按更新日期过滤（支持 `today` 、 `yesterday` 、 `past_week` 、 `past_2_weeks` 、 `past_month` 或月份名称）
`after`	字符串	按创建日期过滤（仅支持晚于指定日期，格式为 `YYYY-MM-DD` ，不可使用未来日期）
`before`	字符串	按创建日期过滤（仅支持早于指定日期，格式为 `YYYY-MM-DD` ）
`app`	枚举值	按数据源过滤（例如 `confluence` 、 `github` 、 `gdrive` 、 `slack` 、 `jira` 、 `notion` ）
`type`	枚举值	按类型过滤： `pull` 、 `spreadsheet` 、 `slides` 、 `email` 、 `direct message` 、 `folder`
`channel`	字符串	按Slack频道名称过滤
`exhaustive`	布尔值	返回所有匹配结果（适用于需要"全部"、"每个"结果的请求）
`sort_by_recency`	布尔值	按最新排序（仅当用户需要"最新"或"最近"内容时使用）

Code Search Filters (code_search) - Inline Query Syntax

代码搜索过滤器（code_search）- 内联查询语法

Code search uses inline filters in the query string:

Person Filters:

```
owner:"person name"
```
or
```
owner:me
```
- Filter by commit creator
```
from:"person name"
```
or
```
from:me
```
- Filter by code file/commit updater

Date Filters:

updated:today|yesterday|past_week|past_month

- Filter by update date

```
after:YYYY-MM-DD
```
- Commits/files changed after date
```
before:YYYY-MM-DD
```
- Commits/files changed before date

代码搜索使用查询字符串中的内联过滤器：

人员过滤器：

```
owner:"person name"
```
或
```
owner:me
```
- 按提交创建者过滤
```
from:"person name"
```
或
```
from:me
```
- 按代码文件/提交更新者过滤

日期过滤器：

updated:today|yesterday|past_week|past_month

- 按更新日期过滤

```
after:YYYY-MM-DD
```
- 按晚于指定日期的提交/文件过滤
```
before:YYYY-MM-DD
```
- 按早于指定日期的提交/文件过滤

Employee Search Filters (employee_search) - Inline Query Syntax

人员搜索过滤器（employee_search）- 内联查询语法

```
reportsto:"manager name"
```
- Find direct reports (NOT for finding who someone reports to)
```
startafter:YYYY-MM-DD
```
- People who started after date
```
startbefore:YYYY-MM-DD
```
- People who started before date

roletype:"individual contributor"|"manager"

- Filter by role type

sortby:hire_date_ascending|hire_date_descending|most_reports

- Sort results

```
reportsto:"manager name"
```
- 查找直接下属（不适用于查找某人的上级）
```
startafter:YYYY-MM-DD
```
- 查找入职时间晚于指定日期的人员
```
startbefore:YYYY-MM-DD
```
- 查找入职时间早于指定日期的人员

roletype:"individual contributor"|"manager"

- 按角色类型过滤

sortby:hire_date_ascending|hire_date_descending|most_reports

- 结果排序方式

Meeting Lookup Filters (meeting_lookup) - Inline Query Syntax

会议查询过滤器（meeting_lookup）- 内联查询语法

Important: meeting_lookup works best with natural language queries. Date filter syntax does NOT work reliably.

Natural language dates (recommended):

"standup last week" - Meetings from last week
"design review past 2 weeks" - Recent meetings
"1:1 with John tomorrow" - Future meetings
"team sync yesterday" - Yesterday's meetings

Other filters that work:

```
participants:"name"
```
- Filter by attendees
```
topic:"subject"
```
- Filter by meeting subject/title
```
extract_transcript:"true"
```
- Include meeting content/transcript

Note: Inline date filters (

after:

before:

) do not work reliably with meeting_lookup. Use natural language dates instead.

重要提示： meeting_lookup搭配自然语言查询效果最佳。日期过滤器语法的可靠性较低。

推荐使用自然语言日期：

"standup last week" - 上周的站会
"design review past 2 weeks" - 近两周的设计评审会
"1:1 with John tomorrow" - 明天与John的一对一会议
"team sync yesterday" - 昨天的团队同步会

其他可用过滤器：

```
participants:"name"
```
- 按参会者过滤
```
topic:"subject"
```
- 按会议主题/标题过滤
```
extract_transcript:"true"
```
- 包含会议内容/记录

注意： 内联日期过滤器（

after:

、

before:

）在meeting_lookup中可靠性较低，请使用自然语言日期替代。

Gmail Search Filters (gmail_search) - Inline Query Syntax

Gmail搜索过滤器（gmail_search）- 内联查询语法

```
from:"person"|"email@domain.com"|"me"
```
- Filter by sender
```
to:"person"|"email@domain.com"|"me"
```
- Filter by recipient
```
subject:"text"
```
- Filter by subject line

has:attachment|document|spreadsheet|presentation

- Filter by attachment type

is:important|starred|read|unread|snoozed

- Filter by email status

```
label:INBOX|SENT|TRASH|DRAFT|SPAM
```
- Filter by folder/label
```
after:YYYY-MM-DD
```
/
```
before:YYYY-MM-DD
```
- Date range

```
from:"person"|"email@domain.com"|"me"
```
- 按发件人过滤
```
to:"person"|"email@domain.com"|"me"
```
- 按收件人过滤
```
subject:"text"
```
- 按主题行过滤

has:attachment|document|spreadsheet|presentation

- 按附件类型过滤

is:important|starred|read|unread|snoozed

- 按邮件状态过滤

```
label:INBOX|SENT|TRASH|DRAFT|SPAM
```
- 按文件夹/标签过滤
```
after:YYYY-MM-DD
```
/
```
before:YYYY-MM-DD
```
- 按日期范围过滤

User Activity Parameters (user_activity)

用户活动参数（user_activity）

The

user_activity

tool uses date range parameters (not query filters):

```
start_date
```
- Start date in YYYY-MM-DD format (inclusive, required)
```
end_date
```
- End date in YYYY-MM-DD format (exclusive, required)

Use for: standup notes, weekly summaries, 1:1 prep, finding documents you touched but forgot.

user_activity

工具使用日期范围参数（而非查询过滤器）：

```
start_date
```
- 开始日期，格式为YYYY-MM-DD（包含该日期，必填）
```
end_date
```
- 结束日期，格式为YYYY-MM-DD（不包含该日期，必填）

适用场景：站会记录、每周总结、一对一会议准备、查找你曾接触但遗忘的文档。

Example Tool Calls

工具调用示例

These examples show the correct syntax for each tool type.

以下示例展示了各工具的正确语法。

Search (Structured Parameters)

搜索（结构化参数）

Pass filters as separate parameters, not in the query string:

search(query="authentication RFC", app="confluence", updated="past_month")
search(query="API design", owner="me", sort_by_recency=true)
search(query="onboarding guide", from="John Smith", after="2024-01-01")

将过滤器作为独立参数传递，而非包含在查询字符串中：

search(query="authentication RFC", app="confluence", updated="past_month")
search(query="API design", owner="me", sort_by_recency=true)
search(query="onboarding guide", from="John Smith", after="2024-01-01")

Code Search (Inline Filters)

代码搜索（内联过滤器）

Include filters directly in the query string:

code_search("authentication handler owner:me updated:past_week")
code_search("payment processor after:2024-06-01 before:2024-12-01")
code_search("API endpoint from:\"Jane Doe\"")

将过滤器直接包含在查询字符串中：

code_search("authentication handler owner:me updated:past_week")
code_search("payment processor after:2024-06-01 before:2024-12-01")
code_search("API endpoint from:\"Jane Doe\"")

Employee Search (Inline Filters)

人员搜索（内联过滤器）

Include filters directly in the query string:

employee_search("engineering manager reportsto:\"VP Engineering\"")
employee_search("backend engineer startafter:2024-01-01")
employee_search("data scientist roletype:\"individual contributor\"")

将过滤器直接包含在查询字符串中：

employee_search("engineering manager reportsto:\"VP Engineering\"")
employee_search("backend engineer startafter:2024-01-01")
employee_search("data scientist roletype:\"individual contributor\"")

Meeting Lookup (Natural Language + Inline Filters)

会议查询（自然语言+内联过滤器）

Use natural language for dates; inline filters for other criteria:

meeting_lookup("my meetings today extract_transcript:\"true\"")
meeting_lookup("standup last week participants:\"John Smith\"")
meeting_lookup("design review past 2 weeks topic:\"architecture\"")

Note: Date filters (

after:

before:

) are documented but don't work reliably in practice. Use natural language dates instead ("today", "yesterday", "last week", "past 2 weeks").

日期使用自然语言，其他条件使用内联过滤器：

meeting_lookup("my meetings today extract_transcript:\"true\"")
meeting_lookup("standup last week participants:\"John Smith\"")
meeting_lookup("design review past 2 weeks topic:\"architecture\"")

注意：日期过滤器（

after:

、

before:

）在文档中有记录，但实际使用时可靠性较低。请使用自然语言日期替代（如"today"、"yesterday"、"last week"、"past 2 weeks"）。

User Activity (Structured Parameters)

用户活动（结构化参数）

Pass date range as separate parameters:

user_activity(start_date="2024-01-08", end_date="2024-01-15")

将日期范围作为独立参数传递：

user_activity(start_date="2024-01-08", end_date="2024-01-15")

Filter Best Practices

过滤器最佳实践

Structured vs Inline Filters:

```
search
```
uses structured parameters - pass filters as separate tool arguments

code_search

employee_search

gmail_search

meeting_lookup

use inline filters in the query string

When to Use Date Filters:

Use
```
updated:
```
for relative timeframes ("last week", "past month")
Use
```
after:
```
/
```
before:
```
for date ranges ("between Jan and March", "since 2024")
Avoid date filters for "latest" or "recent" without specific timeframe
For
```
meeting_lookup
```
, prefer natural language dates over inline filters

Person Filter Guidelines:

Use quotes for multi-word names:
```
from:"John Smith"
```
Use
```
owner:
```
for document creators,
```
from:
```
for broader involvement
Use
```
me
```
when user refers to themselves

Search Strategy:

Start broad, then narrow with filters if too many results
For
```
search
```
: add filter parameters to narrow results
For other tools: add inline filters to the query string
Use the
```
exhaustive
```
parameter on
```
search
```
for exhaustive results ("all", "each", "every")

Common Pitfalls:

Don't use
```
after:
```
with future dates
For
```
search
```
, pass
```
channel
```
and
```
app
```
as separate parameters
Quote multi-word filter values in inline syntax:
```
from:"John Smith"
```

结构化参数与内联过滤器对比：

```
search
```
使用结构化参数 - 将过滤器作为独立工具参数传递
```
code_search
```
、
```
employee_search
```
、
```
gmail_search
```
、
```
meeting_lookup
```
使用内联过滤器 - 将过滤器包含在查询字符串中

日期过滤器使用时机：

相对时间范围使用
```
updated:
```
（如"last week"、"past month"）
具体日期范围使用
```
after:
```
/
```
before:
```
（如"1月至3月之间"、"2024年以来"）
若没有具体时间范围，避免为"最新"或"最近"内容添加日期过滤器
```
meeting_lookup
```
优先使用自然语言日期，而非内联过滤器

人员过滤器指南：

多词姓名需加引号：
```
from:"John Smith"
```
文档创建者使用
```
owner:
```
，更广泛的参与人员使用
```
from:
```
用户指代自己时使用
```
me
```

搜索策略：

先从宽泛的搜索开始，若结果过多再使用过滤器缩小范围
对于
```
search
```
：添加参数过滤器缩小结果范围
对于其他工具：在查询字符串中添加内联过滤器
需要获取全部结果时（如"全部"、"每个"），在
```
search
```
中使用
```
exhaustive
```
参数

常见误区：

不要为
```
after:
```
设置未来日期
对于
```
search
```
，
```
channel
```
和
```
app
```
需作为独立参数传递
内联语法中的多词过滤值需加引号：
```
from:"John Smith"
```

Best Practices

最佳实践

Cite sources: Always include URLs so users can verify
Start broad, then narrow: Use filters to refine if too many results
Combine signals: For expertise, check code + docs + meetings
Respect permissions: Results are filtered by user access
Note when empty: No results is useful information

引用来源：始终包含URL以便用户验证
由宽到窄：若结果过多，使用过滤器逐步缩小范围
多信号结合：如需了解专业知识，同时查看代码、文档和会议记录
尊重权限：结果会根据用户权限进行过滤
注明无结果：无结果也是有价值的信息