Skip to main content
Glama

fluent_download

Download an application's metadata from a ServiceNow instance into a local folder, optionally limited to changes since the last download or run as a background job.

Instructions

Download an application's metadata from the instance into a local folder (now-sdk download). Uses the SDK's default credential (the download command has no alias flag; switch with now-sdk auth --use <alias>). REQUIRES FLUENT_ENABLED=true and WRITE_ENABLED=true (writes local files).

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": {
      "target": "<target>"
    },
    "name": "fluent_download"
  }
}

Input Schema

NameRequiredDescriptionDefault
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.
targetYesFolder to download the metadata into
directoryNoProject directory (contains package.json). Defaults to the working directory.
incrementalNoOnly download changes since the last download

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already mark this as non-read-only, open-world, non-idempotent, non-destructive; the description usefully adds that it writes local files, requires two feature flags, and relies on the SDK default credential. It does not say whether existing files in the target folder are overwritten, which is the main remaining behavioral unknown.

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?

Three sentences, front-loaded with the action and scope, then credentials, then hard requirements. The parenthetical credential note is necessary but slightly dense; no sentence is padding.

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 write-to-disk tool with a fully documented schema, the description covers prerequisites, credential selection, and the fact that local files are produced. The only modest gap is the nature of the returned value (path vs. job_id), which the async parameter doc partially covers.

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% and each of the four parameters (target, directory, incremental, async) is already documented in the schema, including the job_id/20-second fallback behavior. The description adds no parameter-level meaning beyond that, so the baseline of 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 opens with a specific verb and resource — 'Download an application's metadata from the instance into a local folder' — and names the underlying CLI command. It is clearly distinguishable from build/pack/install siblings by the 'instance-to-local' direction, though it does not explicitly route against any named sibling.

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?

Gives concrete preconditions (FLUENT_ENABLED=true and WRITE_ENABLED=true) and resolves the credential question by telling the agent the download command has no alias flag and must be switched via `now-sdk auth --use <alias>`. It stops short of advising when to prefer incremental or async, and states no explicit exclusions.

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