Skip to main content
Glama

generate_reel_captions

Generate a few caption options for a reel with Gemini video understanding, for the connected user to pick from before you schedule or publish it. Sends the video to Google Gemini for analysis (see reeldrop.io/privacy).

Pass source_url the first time for a given video (same kind of link schedule_reel accepts — a direct, publicly-fetchable link, e.g. a Google Drive webContentLink shared "Anyone with the link"). To regenerate options for the SAME video (different topic/tone, or the user didn't like the first batch) pass this call's own video_token back instead of source_url — that skips re-downloading it.

The response's video_token identifies the now-uploaded video. Once the user has picked a caption, pass that video_token (not source_url again) to schedule_reel/schedule_reels_bulk along with the chosen caption text and hashtags — this reuses the same upload instead of re-fetching source_url.

Present all 3 captions as distinct choices — this is a picker, not a single suggestion. For hashtags, hashtags is the full pool Gemini generated (ordered most-to-least relevant, commonly 50+ for a reel); recommended_hashtags is that same list already cut to the top 5 — Instagram's real per-post cap, and what the web app's own composer pre-selects. When calling schedule_reel, pass recommended_hashtags (or a hand-picked subset no larger than 5) as its hashtags argument, not the full hashtags list — nothing server-side trims an oversized list before it reaches Instagram. more_hashtags holds the rest, for a user who wants to swap one of the 5 for an alternative.

Counts against the workspace's monthly caption-generation allowance, same as the web app's caption generator.

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": {
      "workspace_id": "<workspace_id>"
    },
    "name": "generate_reel_captions"
  }
}

Input Schema

NameRequiredDescriptionDefault
nicheNogeneral
topicNo
source_urlNo
video_tokenNo
workspace_idYes
tone_preferenceNoany

Output Schema

NameRequiredDescriptionDefault
nicheNo
captionsYes
hashtagsYes
reel_titleYes
video_tokenYes
more_hashtagsYes
comment_keywordNo
recommended_hashtagsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), it discloses that the video is uploaded and sent to Google Gemini with a privacy link, that uploads are cached and reusable, and that each call counts against the workspace's monthly caption-generation allowance. It even warns that nothing server-side trims oversized hashtag lists before they reach Instagram.

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?

The workflow-critical information is front-loaded and each paragraph carries real operational content. However, a large block explains return fields (hashtags, recommended_hashtags, more_hashtags) despite an output schema existing, which is somewhat redundant 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 6-parameter tool with an output schema, the description covers the full call chain, upload reuse, cost implications, and the downstream scheduling handoff. The main gap is the unexplained generation-shaping parameters (topic, tone_preference, niche) that an agent must set to get useful output.

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 0%, so the description must carry all six parameters; it thoroughly explains source_url and video_token (including accepted link type and mutual exclusivity), but niche, topic, tone_preference, and workspace_id are never described. Partial compensation only, so a mid score.

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?

The description states a specific verb and resource: generate a few caption options for a reel using Gemini video understanding, explicitly framed as a picker for the user before scheduling or publishing. It clearly distinguishes itself from schedule_reel/schedule_reels_bulk by positioning itself upstream in the same workflow.

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

Usage Guidelines5/5

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

It gives explicit when-to guidance: pass source_url the first time, pass video_token to regenerate for the same video, and once a caption is picked, pass video_token (not source_url) to schedule_reel. It also states which hashtag field to forward to schedule_reel and why.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources