Skip to main content
Glama

delimit_generate_scaffold

Creates a new project tree with framework-conformant skeleton for Next.js, APIs, or libraries. Writes standard directory structure, package.json, lint config, and entry-point files in one call.

Instructions

Lay out a fresh project tree with framework-conformant skeleton.

When to use: at project zero, when starting a new Next.js app, API service, or library and you want the standard directory tree, package.json/pyproject.toml, lint config, and entry-point files all written in one call. Typical follow-up is delimit_init to set up governance scaffolding in the new project root. When NOT to use: to add files to an existing project (use delimit_generate_template for single-file scaffolds), to duplicate an existing project (use the shell), or to add a package to an existing project (use the project's own package manager directly).

Sibling contrast: delimit_generate_template writes a single file into an existing project; this writes a NEW project tree. Compared to create-next-app / cookiecutter, this routes the scaffold through the Delimit bridge so the resulting project can later be wired into delimit_init governance with no manual cleanup.

Side effects: writes MANY new files and directories under a new name/ root via backends.generate_bridge.scaffold. packages is coerced from a comma string to a list via _coerce_list_arg (malformed values short-circuit). No license gate. No ledger write, no notification. The backend determines collision behaviour if name/ already exists — call against a fresh target.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_typeYesProject flavour, e.g. "nextjs", "api", "library". Required.
nameYesProject name (becomes the root directory). Required.
packagesNoPackages to include — either a comma string or list.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It details side effects: writes many new files, coerces packages from comma string to list, no license gate, no ledger write, no notification, and backend-determined collision behavior. This is thorough, though it could explicitly state that it's a write operation (implicitly clear).

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?

The description is well-structured with clear sections (purpose, when to use, when not to use, sibling contrast, side effects) and is concise at around 100 words. Each sentence adds value without redundancy.

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?

Given the tool's complexity (project scaffold with side effects) and the presence of an output schema (so return details are covered), the description provides sufficient context: side effects, error conditions (malformed packages), collision behavior, and prerequisites. It is complete for an agent's decision-making.

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%, but the description adds meaningful context beyond the schema: explains the coercion of the `packages` parameter from comma string to list and that malformed values short-circuit, and clarifies that `name` becomes the root directory. This adds value.

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 explicitly states the tool's purpose: 'Lay out a fresh project tree with framework-conformant skeleton.' It clearly identifies the verb (lay out) and resource (fresh project tree), and distinguishes from sibling tools like delimit_generate_template by specifying that this writes a new project tree rather than a single file into an existing project.

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?

The description provides explicit when-to-use guidance (project zero, new app/service/library) and when-not-to-use guidance (adding files to existing project, duplicating, adding packages). It lists alternative tools (delimit_generate_template, shell, package manager) and mentions a typical follow-up (delimit_init).

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