Skip to main content
Glama

Create Department

create_department

Creates a project-specific department with scoped ownership, a dedicated subagent, and organization records so domain work is delegated while the orchestrator coordinates.

Instructions

Lập bộ phận theo dự án: hồ sơ docs/departments/<mã>/, subagent .claude/agents/dept-<mã>.md, thêm vào ORGANIZATION.md.

Sau khi lập, mọi việc thuộc lĩnh vực của bộ phận được giao cho subagent này; Orchestrator chỉ điều phối. model và effort là mặc định của bộ phận; Orchestrator ghi đè theo từng việc khi giao (ORGANIZATION.md §5.1).

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": {
      "project_dir": "<project_dir>",
      "code": "<code>",
      "name": "<name>",
      "domain": "<domain>",
      "owns": "<owns>"
    },
    "name": "create_department"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesMã viết hoa, ví dụ PLATFORM, TRUST
nameYesTên bộ phận, ví dụ Nền tảng
ownsYesVùng thư mục sở hữu, ví dụ `src/`, `tests/`
modelNoModel mặc định của subagent: inherit, sonnet, opus, haiku hoặc mã model; việc soạn tài liệu, rà soát, khảo sát nên dùng model nhẹinherit
domainYesLĩnh vực phụ trách, một câu
effortNoMức suy nghĩ mặc định của subagent; để trống thì theo phiên gọi
decisionNoMã QT lập bộ phận nếu đã ghi
disciplineNoKỷ luật riêng của bộ phận, mỗi dòng một luật, ví dụ chạy test nào trước khi báo xong
project_dirYesĐường dẫn tuyệt đối tới gốc repo dự án

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already mark this as a non-read, non-destructive write, and the description goes meaningfully beyond them: it lists the files and folders created, explains the downstream routing rule (subagent owns the domain, Orchestrator only coordinates), and clarifies the model/effort default-and-override contract. It omits idempotency/overwrite behavior and error conditions, keeping it short of a 5.

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

Conciseness5/5

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

Two short paragraphs, front-loaded with the artifact list, then the routing/override rules. Every sentence contributes operational information with no filler.

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

Completeness4/5

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

With 9 parameters, full schema coverage, annotations, and an output schema, the description covers what an agent needs to call it correctly and understand the consequences. The main remaining gap is edge-case behavior (existing code, invalid project_dir) rather than core semantics.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning for model and effort by framing them as department defaults that the Orchestrator overrides per task per ORGANIZATION.md §5.1. That override semantic is not derivable from the schema alone.

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 verb+resource (establish a department for the project) and enumerates the concrete artifacts produced: docs/departments/<code>/, .claude/agents/dept-<code>.md, and an entry in ORGANIZATION.md. It is clearly distinct from sibling tools like refresh_departments or scaffold_project, though it never names them 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 implied by the naming and by the note that once established, all work in the department's domain routes to the subagent. However, there is no explicit when-to-use / when-not guidance, no prerequisite stated (e.g. must ORGANIZATION.md exist first), and no mention of behavior if the department already exists.

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