Skip to main content
Glama

delimit_init

Initialize project governance: create policies, ledger, and permissions allowlist.

Instructions

Initialize Delimit governance scaffolding for a project.

When to use: once per project, the first time you adopt Delimit — creates .delimit/policies.yml, ledger directory, and (optionally) a project .claude/settings.json with a reasonable allowlist. When NOT to use: to load an existing config (use delimit_project_config action="load") or to discover Delimit's capabilities for a project (delimit_scan).

Sibling contrast: delimit_project_config manages the config after init; delimit_scan inspects what could be governed; this is the one-time initializer.

Side effects: creates .delimit/policies.yml + ledger dir; chmod 755 on .delimit/, chmod 600 on .delimit/secrets/*; writes a project .claude/settings.json with an Edit/Write/Bash allowlist if missing. Pass no_permissions=True to skip the permission step.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_pathNoProject root directory. Default "." (cwd)..
presetNoPolicy preset — "strict", "default", "relaxed".default
no_permissionsNoSkip filesystem permission auto-config (LED-269).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

Lists side effects: creates .delimit/policies.yml, ledger dir, and optional settings.json, plus chmod operations. Also mentions no_permissions parameter to skip permission step. Since no annotations exist, the description fully covers behavioral traits.

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?

Well-structured with labeled sections, front-loaded key info, no wasted sentences.

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

Completeness5/5

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

Covers purpose, usage, side effects, parameters, and sibling contrast. Output schema exists so return value explanation is optional. Complete for a one-time initialization tool.

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 baseline is 3. The description adds context linking no_permissions to permission side effect, but doesn't add new meaning beyond schema descriptions for project_path and preset. Slight value uplift.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it initializes Delimit governance scaffolding, lists files created, and distinguishes from siblings by explicitly naming delimit_project_config and delimit_scan.

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

Usage Guidelines5/5

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

Provides explicit 'when to use' (once per project, first time) and 'when NOT to use' (load config or discover capabilities), along with alternative tool names.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/delimit-ai/delimit-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server