Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_office_create

Create or refresh an office in one declarative call with agents, optional chains, cron, and a home repo; idempotent updates appear immediately in the 3D agents-flow view.

Instructions

Create or refresh a whole office (department) in one declarative call: flow + agents + optional chains, cron and home repo. Agents get smart defaults — with repo set they become claude_code executors with native FS tools jailed to that cwd. Idempotent (flow matches by name, agents by slug). The office appears in the 3D agents-flow view immediately.

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": {
      "name": "<name>",
      "agents": "<agents>"
    },
    "name": "kernel_office_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
cronNo
nameYesOffice name, e.g. 'Marketing'. Idempotency key.
repoNoHost repo path ('~' expands). Implies claude_code agents with cwd there.
colorNoHex color of the 3D room, e.g. '#16a34a'. Default: palette pick.
agentsYes
disciplineNoShared preamble prepended to every agent prompt. false = none. Default: generic office discipline.
previewUrlNoURL shown as a clickable preview link in the dashboard.
descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses idempotency keys (flow by name, agents by slug), an implicit defaulting behavior (setting `repo` turns agents into claude_code executors with native FS tools jailed to that cwd), and a visible side effect (the office appears in the 3D agents-flow view immediately). It stops short of saying what 'refresh' does to existing agents whose prompts differ, or what the call returns.

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?

Three sentences, front-loaded with the verb and scope, then defaults, then idempotency, then the visible outcome. Every clause carries information an agent needs and nothing is repeated from the schema verbatim.

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?

For an 8-parameter nested provisioning tool with no output schema and no annotations, the description covers the essentials: what gets created, defaulting rules, idempotency, and a user-visible effect. The remaining gap is the refresh/overwrite semantics and the response shape, which matter for an agent deciding whether it is safe to re-run.

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 63% with nested objects, so the description must add cross-parameter meaning — and it does, notably that `repo` implies claude_code agents with cwd set there and that agents receive 'smart defaults.' It also reinforces `name` as the idempotency key and slug auto-derivation. It adds less for cron, discipline, color, and previewUrl, which the schema already documents.

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 opens with a specific verb+resource+scope: 'Create or refresh a whole office (department) in one declarative call,' then enumerates exactly what is bundled (flow + agents + optional chains, cron, home repo). That clearly separates it from the single-agent and single-flow siblings like kernel_agents_create and kernel_agents_flows_create, though it never names those alternatives 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 rather than stated: 'in one declarative call' and 'Create or refresh' suggest this is the batch/provisioning entry point, and idempotency is spelled out (flow matches by name, agents by slug). However, there is no explicit when-not-to-use guidance versus kernel_agents_create or kernel_office_pack_import, and no mention of prerequisites or permissions.

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

Deploy Server

Other Tools