Skip to main content
Glama

fluent_init

Create or convert ServiceNow Fluent applications: initialize a new now-sdk project, apply a template, or migrate a legacy scoped app into source.

Instructions

Create a new Fluent (now-sdk) application, apply a template to an existing one, or convert a legacy scoped app into Fluent source (from = app sys_id on the instance, or a local folder). Runs now-sdk init in the given directory. REQUIRES FLUENT_ENABLED=true and WRITE_ENABLED=true.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "fluent_init"
  }
}

Input Schema

NameRequiredDescriptionDefault
authNonow-sdk credential alias (optional)
fromNoConvert a legacy app: its sys_app sys_id on the instance, or a local folder path
nameNoApplication name (--appName)
scopeNoScope name, e.g. x_acme_app (max 18 chars, vendor prefix if applicable)
installNoRun npm install in the new project so it builds straight away (default true)
templateNoProject template
directoryNoDirectory to create the project in (defaults to the server working directory)
package_nameNonpm package name (--packageName). Defaults to a slug of name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv5.0.1
    • addedInput schema / properties / auth
      Added value: +{
      +  "description": "now-sdk credential alias (optional)",
      +  "type": "string"
      +}
    • changedInput schema / properties / directory / description
      Previous value: -"Target directory (optional, defaults to cwd)"New value: +"Directory to create the project in (defaults to the server working directory)"
    • addedInput schema / properties / from
      Added value: +{
      +  "description": "Convert a legacy app: its sys_app sys_id on the instance, or a local folder path",
      +  "type": "string"
      +}
    • addedInput schema / properties / install
      Added value: +{
      +  "description": "Run npm install in the new project so it builds straight away (default true)",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / name / description
      Previous value: -"Project name"New value: +"Application name (--appName)"
    • addedInput schema / properties / package_name
      Added value: +{
      +  "description": "npm package name (--packageName). Defaults to a slug of name.",
      +  "type": "string"
      +}
    • addedInput schema / properties / scope
      Added value: +{
      +  "description": "Scope name, e.g. x_acme_app (max 18 chars, vendor prefix if applicable)",
      +  "type": "string"
      +}
    • changedInput schema / properties / template / description
      Previous value: -"Project template (optional)"New value: +"Project template"
    • addedInput schema / properties / template / enum
      Added value: +[
      +  "base",
      +  "javascript.basic",
      +  "javascript.react",
      +  "typescript.basic",
      +  "typescript.react",
      +  "typescript.vue",
      +  "javascript.aiux",
      +  "javascript.aiux-extension"
      +]
    • changedInput schema / required
      Previous value: -[
      -  "name"
      -]New value: +[]
  2. Addedv4.9.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare this is a mutating, non-idempotent, open-world operation, so the safety bar is partly covered. The description adds real value beyond them by naming the executed command and the two required environment flags. It does not disclose side effects on a pre-existing/non-empty target directory or what happens when `install` triggers network access.

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 sentences, front-loaded with the three operation modes before the execution detail and the prerequisites. No filler, and the ordering puts the decision-relevant information first.

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, all-optional scaffolding tool with full schema coverage and annotations, the description covers what it does, how it runs, and what must be enabled. It leaves return values and behavior on conflicting/existing directories unstated, which is a modest gap given there is no output schema.

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

Parameters3/5

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

Schema description coverage is 100%, so every parameter is already documented in the schema and the baseline is 3. The description's parenthetical about `from` (sys_id or local folder) essentially restates the schema text, and it adds only the loose notion that options apply to 'the given directory' rather than any new per-parameter semantics.

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?

States three concrete operations on a specific resource: create a new Fluent/now-sdk app, apply a template to an existing app, or convert a legacy scoped app. The underlying command (`now-sdk init`) anchors it further. It does not explicitly contrast itself with plausible siblings such as fluent_transform or fluent_build, so it stops short of a 5.

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?

The three enumerated modes give the agent clear conditions for selecting this tool, and the prerequisite env flags (FLUENT_ENABLED, WRITE_ENABLED) are a useful gate. There are no explicit exclusions or named alternatives for cases like 'I already have Fluent source and just want to build it'.

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