Skip to main content
Glama
unofficial-instagram-mcp

unofficial-instagram-mcp

ig_selftest

Destructive

Runs Instagram MCP self-tests to verify read-only tools safely, or with required gates, test write tools on disposable content and delete it. Use full mode only on a secondary account.

Instructions

Jalankan self-test resmi. Level "safe" (default): hanya tool baca, aman di akun mana pun. Level "full": menguji SEMUA tool tulis pada konten buatan sendiri lalu MENGHAPUS semuanya di akhir; gerbang keras IG_SELFTEST_FULL=true + IG_DRY_RUN=false + IG_SELFTEST_ACCOUNT harus sama dengan akun login. PERINGATAN: level full hanya di akun kedua, jangan akun utama.

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": "ig_selftest"
  }
}

Input Schema

NameRequiredDescriptionDefault
levelNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true) by disclosing that the default 'safe' mode is read-only while 'full' writes test content and then DELETES all of it, plus the exact environment-variable gates that must be satisfied. The account-safety warning adds real operational context the annotations cannot express.

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?

Front-loaded and well ordered: purpose, then safe mode, then full mode, then the hard gates, then the warning. Dense but every clause carries operational meaning; only the word 'resmi' and the all-caps emphasis are slightly expendable.

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?

Covers the decision-critical facts for a single-parameter, destructive diagnostic: mode semantics, gating, and account restriction. With no output schema present, it does not say what the self-test returns or how failures are reported, which is the one remaining gap.

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

Parameters5/5

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

Schema coverage is 0% and the schema declares no enum for 'level', so the description must carry the full burden — and it does, naming both accepted values, marking 'safe' as the default, and spelling out the very different consequences and gating requirements of each.

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 resource ('Jalankan self-test resmi') and immediately decomposes it into two named modes, 'safe' and 'full', so an agent knows exactly what the tool does and that it is a diagnostic, not a normal content operation like the sibling post_* or dm_* tools.

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 explicit context per level: 'safe' is read-only and safe on any account, 'full' exercises all write tools and is only for a secondary account, with a hard warning against the main account. It also states prerequisites (IG_SELFTEST_FULL=true, IG_DRY_RUN=false, IG_SELFTEST_ACCOUNT matching the logged-in account), though it does not name a sibling alternative for verifying status (e.g. ig_status).

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