Skip to main content
Glama

Write captions

klynx_write_captions

Use this when the user wants social media captions written from a short text description and does not need a photo enhanced, for example to post with a photo they already have. Needs subject (text, up to 200 characters); platforms (any of instagram, facebook, tiktok, linkedin; default all four), tone and length are optional. Business name, type, location and English spelling come from the connected Klynx account, so do not ask the user for them. No photo is used, so no alt text is returned. Returns one caption per platform, each with up to five hashtags, plus post ids and the posts remaining in the plan allowance. Uses one post per platform from the account's plan allowance, as the Klynx web app would; a job the allowance does not cover is refused with plan_allowance_exhausted before any work and nothing is charged. On the free plan, captions paid from the plan allowance end with a short Made with klynx.ai line. A job that fails uses nothing from the allowance. It only creates drafts in the Klynx account: it does not publish, schedule or post anything. A caption-only draft needs a photo applied in the Klynx web app before it can be published.

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": {
      "subject": "<subject>"
    },
    "name": "klynx_write_captions"
  }
}

Input Schema

NameRequiredDescriptionDefault
toneNoOptional. Caption tone: Friendly, Professional, Casual, Enthusiastic, Informative or Humorous. Defaults to Casual.
lengthNoOptional. Caption length for every platform: short, medium or long. By default Instagram, Facebook, TikTok and LinkedIn are medium.
subjectYesShort description of what the post is about (up to 200 characters are used).
platformsNoPlatforms to write for. Any of instagram, facebook, tiktok, linkedin. Defaults to all four.
idempotency_keyNoOptional key that makes a retry safe: a key already used is never charged or run twice.

Output Schema

NameRequiredDescriptionDefault
captionsYes
post_idsYesThe saved posts in the Klynx account, in caption order.
publishedYesAlways false: this tool only creates drafts and never publishes, schedules or posts anything. To post a Facebook or Instagram draft, use klynx_preview_publish, then klynx_publish_now or klynx_schedule_post once the user approves.
operation_idYes
posts_remainingYesPosts left in the plan allowance after this job, or null when there is no limit.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations: it discloses plan-allowance billing per platform, pre-flight refusal with plan_allowance_exhausted at no charge, that failures consume nothing, the free-plan watermark, and that it only creates drafts rather than publishing or scheduling. What it omits is the role of idempotency_key in retry safety, which the schema covers rather than the description.

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 with the use case, then layered into inputs, returns, billing and side effects, with no filler sentences. It is on the long side, but each sentence carries distinct operational information (cost, refusal, watermark, draft-only), so the length is largely earned.

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?

For a paid, side-effecting creation tool with five parameters, the definition covers invocation, account-sourced inputs, outputs (captions, hashtags, post ids, remaining allowance), billing semantics and the draft-only limitation. With an output schema present, nothing an agent needs to call it correctly is missing.

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%, so the baseline is 3, but the description adds real meaning: it restates the 200-character subject limit, platform defaults, and that tone/length are optional. Most valuably, it explains why account-level fields are not parameters at all ('come from the connected Klynx account'), which is information the schema cannot convey.

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 ('social media captions written from a short text description') plus the scope boundary that it uses no photo. It explicitly contrasts with the photo-enhancement path ('does not need a photo enhanced'), so an agent can separate it from the photo/publish siblings without opening their schemas.

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?

Opens with an explicit trigger condition ('when the user wants social media captions... for example to post with a photo they already have') and an exclusion (no photo enhancement needed). It also gives a concrete anti-pattern to avoid: don't ask the user for business name, type, location or spelling because those come from the connected account.

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