Skip to main content
Glama

fluent_install

Install or update a built Fluent app on a ServiceNow instance; optionally report the latest install or reinstall first, which discards instance-only metadata not present locally.

Instructions

Install or update a built Fluent app on the instance (now-sdk install). info=true only reports the most recent install. reinstall=true uninstalls first and DISCARDS on-instance metadata not present locally. 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_install"
  }
}

Input Schema

NameRequiredDescriptionDefault
authNonow-sdk credential alias (optional)
infoNoOnly show information about the most recent install of this app
asyncNoRun as a background job and return a job_id at once. Poll it with get_job. Calls that take longer than about 20 seconds switch to a job on their own.
demo_dataNoInstall demo data (default true)
directoryNoProject directory (contains package.json). Defaults to the working directory.
reinstallNoUninstall and reinstall (on-instance-only metadata is lost)
skip_flow_activationNoDo not publish flows after install

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A4/5.0
Behavior4/5

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

Beyond the annotations, the description discloses environment-flag prerequisites and the conditional data loss from reinstall=true ('DISCARDS on-instance metadata not present locally'), which the schema only states more mildly. Note the tension with destructiveHint=false: the destructive path exists but is gated behind a non-default flag, and the description is the more accurate source. Return/output behavior for a successful install is not described.

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?

Four short sentences, front-loaded with the action, then the mode flags, then the hard prerequisites. Capitalized warnings are used sparingly and only where consequences are severe; there is no filler.

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 a mutation tool with seven optional parameters, no output schema, and a genuine data-loss path, the description covers the action, prerequisites, and the risky flag adequately. It stops short of describing what a successful install returns or how failures/jobs surface (async defers to get_job only in the schema), which would complete the picture.

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 coverage is 100%, so all seven parameters are already documented in the schema, including the on-instance metadata caution for reinstall. The description largely restates the info and reinstall flags (albeit with emphasis) and adds nothing about auth, directory, async, demo_data, or skip_flow_activation, so the baseline 3 applies.

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 states a specific verb+resource ('Install or update a built Fluent app on the instance') and anchors it to the underlying command (`now-sdk install`). The word 'built' implicitly separates it from fluent_build, but no sibling is named outright, so the differentiation is inferred rather than explicit.

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?

It gives real usage conditions: info=true is report-only, reinstall=true triggers uninstall-first, and the tool REQUIRES FLUENT_ENABLED=true and WRITE_ENABLED=true. What it does not state is the ordering relative to fluent_build or which sibling to choose for a plain deploy versus a CI/CD path.

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