Skip to main content
Glama

ACTION_WORKSPACE

Read, write, append, list, search, and delete local workspace entries for results, notes, and images users view in the app's Workspace page.

Instructions

读写本机工作区条目(结果、笔记、图片),用户在 App「工作区」页查看。输出:workspace_id, workspace_kind, workspace_content, workspace_path, workspace_list, workspace_count, workspace_name, workspace_success, workspace_error。字符串参数支持 ${var} 插值;结果以变量快照 JSON 返回。

Input Schema

NameRequiredDescriptionDefault
idNoread/delete:条目 id,优先于 name
tagNolist:按标签筛选
kindNowrite:条目类型 text(默认)/ json / image;list:按类型筛选,可多一个 record;其余为别名
nameNo条目显示名(write/append 必填;read/delete 可用它或 id 定位)
tagsNowrite/append:标签,逗号分隔
limitNolist:最多返回条数(1–200)(默认 20)
queryNosearch:找最近一条名字/标签/内容包含它的笔记(文本或 JSON);空=最近一条
actionNo操作类型(默认 write)
contentNowrite/append:内容,支持 ${var};kind=json 时须为合法 JSON,kind=image 时为 base64
requireNo执行后要求为 true 的变量名(如 click_success),不满足按出错处理
on_errorNo节点出错时:skip=跳过继续(默认),stop=停止整个工作流
overwriteNowrite:同名同类时覆盖;false 则自动改名为「名字 (2)」(默认 true)
image_pathNokind=image:图片文件路径(代替 content),上限 8MB
output_varNoread/search 的内容 / list 的 JSON 数组存到的变量名(默认 workspace_content / workspace_list)
node_timeout_msNo单节点超时毫秒,0=不限;默认 30 分钟

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden, yet it only discloses that results come back as a variable-snapshot JSON and that ${var} interpolation is supported. It says nothing about the destructive nature of delete, overwrite/rename semantics, the 8MB image cap, or timeout/error handling, all of which an agent needs to call this safely.

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?

Two compact sentences with the purpose front-loaded, followed by the output field list. Nothing is padded, though the enumerated output fields are dense and somewhat redundant as a run-on list.

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

Completeness3/5

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

For a 15-parameter, six-action tool with no output schema, listing the returned fields and the interpolation behavior is genuinely useful compensation. However, the description omits the risk profile of the mutating actions (delete, overwrite, image size limit) and the per-action branching, leaving gaps relative to the tool's 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% and each of the 15 parameters already documents its role per action, so the baseline is 3. The description only adds cross-cutting meaning — string interpolation with ${var} and the default output variable names — rather than clarifying individual parameters.

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 a concrete verb and resource: read/write local workspace entries of types results, notes and images, viewable on the App's Workspace page. The resource is specific enough to separate it from siblings like ACTION_CLIPBOARD and ACTION_APP_SEARCH, though it never names an alternative explicitly.

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?

Usage is only implied: the parenthetical '(results, notes, images)' and the note that users view entries in the App Workspace page hint at persistence use cases. There is no explicit statement about when to choose this over sibling actions such as ACTION_CLIPBOARD or ACTION_SET_VARIABLE, and no exclusions or prerequisites.

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