Skip to main content
Glama

generate_carousel_captions

Write caption options for a carousel from its slides, with Google Gemini (see reeldrop.io/privacy) — the Carousel Lab's own caption step.

Present all the captions as distinct choices and let the user pick (or edit one); never post one they haven't approved. Pass recommended_hashtags (at most 5) as schedule_post's hashtags. user_context adds anything the caption should know (an offer, a comment keyword, the audience).

Counts against the workspace's monthly caption-generation allowance.

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>",
      "carousel_id": "<carousel_id>"
    },
    "name": "generate_carousel_captions"
  }
}

Input Schema

NameRequiredDescriptionDefault
carousel_idYes
user_contextNo
workspace_idYes

Output Schema

NameRequiredDescriptionDefault
nicheNo
titleYes
captionsYes
hashtagsYes
carousel_idYes
more_hashtagsYes
comment_keywordNo
recommended_hashtagsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly=false and openWorld=true, and the description adds real value on top: it names the third-party provider and points to a privacy URL, and it discloses that the call counts against the workspace's monthly caption-generation allowance. That quota constraint is exactly the kind of operational context annotations cannot express. It does not describe whether repeated calls yield varied results beyond what idempotentHint=false implies.

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 first sentence front-loads the action and the model provider, and the subsequent sentences each carry a distinct instruction (approval rule, hashtag handoff, context field, quota). The inline privacy URL and parenthetical asides make it slightly cluttered, but no sentence is pure filler.

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?

An output schema exists, so the description rightly omits return-value explanation. It covers the provider/open-world disclosure, quota cost, the approval workflow, and the meaning of the one non-obvious input, which is everything an agent needs to call this correctly and use the result responsibly.

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 the parameter burden, and it does so only partially. `user_context` is explained well ("anything the caption should know — an offer, a comment keyword, the audience"), but `workspace_id` and `carousel_id` are left to inference from phrasing. It also references `recommended_hashtags`, which is an output field rather than an input, offering no clarification of the remaining two inputs.

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?

The description states a specific verb and resource ("Write caption options for a carousel from its slides") and names the producing mechanism (Google Gemini), which clearly separates it from generate_reel_captions and generate_carousel_slides by resource. It stops short of explicitly contrasting itself with the reel variant, so a 4 rather than a 5.

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?

It gives concrete downstream workflow guidance: present captions as distinct choices, let the user pick or edit, and never post one unapproved. It also routes the output of `recommended_hashtags` into schedule_post's hashtags, which is an explicit next-step handoff. It lacks any statement of when this tool is *not* appropriate relative to sibling caption tools.

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