Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_agents_workspace_apply

Declares and prepares an office's home folder contents: clones git repos, seeds files, and installs MCP servers and skills for Claude Code agents. Replaces the previous spec.

Instructions

Declare what an office's home folder must contain and prepare it now: git repos to clone (at a branch), files to seed, MCP servers and skills for every claude_code agent working in the home. Replaces the previous spec. Existing checkouts are never re-cloned or reset; seeded files only replace an existing one when overwrite is true. Runs of the office wait for the home to be ready and fail with the reason when it can't be prepared.

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": {
      "flow_id": "<flow_id>",
      "spec": "<spec>"
    },
    "name": "kernel_agents_workspace_apply"
  }
}

Input Schema

NameRequiredDescriptionDefault
specYesWorkspaceSpec object or JSON: { "git": [{ "repo", "branch"?, "path"?, "depth"? }], "files": [{ "path", "content", "overwrite"? }], "mcp_servers": { name: config }, "skills": [slug] }
flow_idYesOffice (flow) ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses replacement semantics, that existing checkouts are never re-cloned or reset, that seeded files only overwrite when the flag is true, and that dependent office runs block and fail with a reason. It leaves open what happens to entries removed from the spec (are stale files deleted?) and whether the call returns a summary of what was prepared.

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?

Four dense sentences, each carrying distinct information: the declaration, the replacement semantics, the non-destructive guarantees, and the run-blocking consequence. The declarative purpose is front-loaded; nothing is filler, though the phrasing is compact enough to require a careful read.

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 unannotated mutation tool with a nested spec object and no output schema, this covers the essential shape: what gets created, what is protected from mutation, and how failures surface to dependents. The main gaps are cleanup semantics for omitted entries and any indication of what the call reports back.

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 already 100%, including a nested WorkspaceSpec shape, so the baseline is 3; the description adds real meaning by explaining what each spec section accomplishes and the overwrite gating rule for files. The flow_id parameter gains no elaboration beyond the schema's 'Office (flow) ID'.

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 gives a specific verb and resource: declare the contents of an office's home folder and prepare it now, covering git repos, seeded files, MCP servers and skills. It is clearly distinct in intent from kernel_agents_workspace_get, but it never names that read counterpart, so the differentiation remains implicit rather than stated.

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

Usage Guidelines4/5

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

'Replaces the previous spec' plus 'Runs of the office wait for the home to be ready' establishes clear context: this is the declarative write step that must precede an office run. There is no explicit exclusion or named alternative, and no mention of prerequisites such as permissions or whether this can be safely re-invoked with the same spec.

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