Skip to main content
Glama

fluent_dependencies

Downloads dependencies declared in now.config.json plus TypeScript type definitions, and registers new dependency records via add and scope.

Instructions

Download the dependencies declared in now.config.json plus TypeScript type definitions (Script Include types, glide.*.d.ts, ChoiceSets). Use add + scope to register new dependency records. Runs now-sdk dependencies. REQUIRES FLUENT_ENABLED=true and WRITE_ENABLED=true (writes local files).

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_dependencies"
  }
}

Input Schema

NameRequiredDescriptionDefault
addNoTable of dependency items to add, e.g. sys_security_acl, actions, triggers
authNonow-sdk credential alias (optional)
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.
scopeNoScope of the added dependencies (required with add), e.g. global
sys_idsNosys_ids to add (with add)
directoryNoProject directory (contains package.json). Defaults to the working directory.
fluent_onlyNoOnly download Fluent types from now.config.json dependencies
type_defs_onlyNoOnly download script type definitions

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?

Annotations already declare openWorldHint=true and readOnlyHint=false; the description adds genuinely new behavior: the required environment gates and the fact that the call writes local files, which explains why it is not read-only. It does not say whether existing generated files are overwritten or what the local output looks like.

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?

Four short sentences, front-loaded with what is downloaded, then the alternate mode, then prerequisites. Every sentence carries information; the `now-sdk dependencies` command mapping is the least essential line but still useful context.

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?

For an 8-parameter tool with no output schema, the definition covers the default download behavior, the type-definition scope, the add/scope alternative mode, the underlying CLI command, and the enabling flags. The remaining gap (overwrite semantics for local files) is minor and not blocking for correct invocation.

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 every parameter is already documented, including add and scope in detail. The description reinforces the add+scope pairing and clarifies what the type definitions actually are, but adds no syntax, format, or constraint details beyond the schema, so 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?

Names a specific verb and resource: downloads dependencies declared in now.config.json plus TypeScript type definitions (Script Include types, glide.*.d.ts, ChoiceSets), and identifies the underlying command `now-sdk dependencies`. It never names a sibling (e.g. fluent_download) to contrast with, but the resource scope is narrow enough that an agent can tell what it does.

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?

"Use add + scope to register new dependency records" gives an explicit condition that selects the second mode, and the prerequisite flags (FLUENT_ENABLED, WRITE_ENABLED) tell the agent when the call is even permitted. It stops short of exclusions or naming an alternative tool for dependency listing versus downloading.

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