Instadata — Instagram Data API

Summarise a video

get_summary

Read-onlyIdempotent

Short LLM summary of what a public video actually says, built on its transcript. Instagram only. Credits: 4 per call plus 20 per started minute of video. Input: url.

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": {
      "url": "<url>"
    },
    "name": "get_summary"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Full public URL of the post, video, profile or page.

Output Schema

Name	Required	Description
`data`	Yes	The endpoint's payload: one object, or an array for list calls.
`meta`	No	count, limit and next_cursor on list calls; credits_charged, credits_remaining and cache (hit or miss) on billed calls; limit_clamped when fewer items were requested upstream than the balance could cover; limit_capped when a free account's request was lowered to the free tier's 5-item ceiling.
`request_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the description rightly focuses on what they don't cover: per-call credit cost (4) plus a duration-based 20-per-started-minute charge, and the Instagram-only restriction. It stops short of disclosing output length limits or failure behavior for videos without transcripts, but the cost model is a material addition.

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 tight sentences, front-loaded with purpose, then platform constraint and pricing. The trailing 'Input: url' is redundant with the schema and could be dropped, but overall there is very little waste.

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 one-parameter read tool with an output schema and full annotation coverage, the description supplies the two things structured fields cannot: platform restriction and credit pricing. Only minor gaps remain, such as behavior when no transcript is available.

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% and the single url parameter is fully documented in the schema, so the description's 'Input: url' adds nothing. Baseline 3 applies since the schema carries the parameter semantics.

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 ('short LLM summary of what a public video actually says') plus the mechanism ('built on its transcript') and the scope ('Instagram only'). An agent can distinguish it from get_transcript in the sibling list without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Instagram only' constraint and the fact that the output derives from a transcript imply when this tool is appropriate versus get_transcript, but the routing is left to inference. There is no explicit when-to-use/when-not statement or named alternative.

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

All Instadata — Instagram Data API tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?