Skip to main content
Glama

Get app integration code

get_integration_guide
Read-onlyIdempotent

Generates working integration code for adding Importly to your Node, Next.js, Python, or cURL app, covering API key setup, backend jobs, webhook/polling results, and error handling.

Instructions

Get working code that builds Importly into the user's own app (Node, Next.js, Python, or cURL): API key setup, starting a job from the backend, receiving the result by webhook or polling, and error handling. Call this first whenever the user is building or changing an app that takes video or audio links and needs the file, a transcript, or metadata. The app reads the same API key from its server environment. Does not call the API or use credits.

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": "get_integration_guide"
  }
}

Input Schema

NameRequiredDescriptionDefault
useCaseNoWhat the app needs: import (download), transcribe, or metadata (default import)
languageNoLanguage/framework of the user's app (default node)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, destructive=false, closed-world), so the bar is lower, and the description still adds real behavioral facts: it is a code-generation/read tool, it consumes no credits, and the generated app reads the same API key from its server environment. It stops short of describing the response shape (e.g., how the code is presented), which is the remaining gap.

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?

Three sentences, all load-bearing, front-loaded with what the tool produces before the when-to-use condition. No filler or repetition of the title.

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?

With only two optional enum parameters and no output schema, the description is close to complete: it enumerates what the returned code covers and reassures the agent that no credits are spent. A brief note on how the code is returned (single code block, multiple files) would make it fully self-sufficient.

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% and both enums carry their own descriptions, so baseline is 3; the description goes slightly further by mapping the use cases ('the file, a transcript, or metadata') to the useCase values and listing the four languages matching the language enum. It does not state what the defaults are, though the schema already does.

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?

States a specific verb and product ('Get working code that builds Importly into the user's own app') and enumerates exactly what the code covers: API key setup, backend job start, webhook/polling result retrieval, and error handling. 'Does not call the API or use credits' cleanly separates it from the sibling tools that actually perform imports and transcriptions.

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 a concrete trigger: 'Call this first whenever the user is building or changing an app that takes video or audio links and needs the file, a transcript, or metadata.' That is clear when-to-use guidance, but it never names a sibling to use for the inverse case (actually running a job), leaving the agent to infer the routing from 'does not call the API'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.