Skip to main content
Glama

Enhance photo and write captions

klynx_create_post_pack

Use this when the user has a photo or image they have chosen for a post about their business (their own photo of food, drinks, a shop, a salon, their work, team or premises, or a stock or other image they have the right to use) and wants it made ready to post. Klynx works best with the business's own photos: it enhances what is really there and never invents anything. Enhances the image for colour, light and sharpness with nothing added to or removed from the scene (images under 1280px on the longest edge are upscaled, which can add fine detail) and writes one caption per platform (instagram, facebook, tiktok, linkedin) in the business's voice, with alt text and up to five hashtags. Enhancement is only available together with captions. Needs image_url (https) or upload_id (from klynx_request_photo_upload) for an image at least 800px on its longest edge; platforms, subject, length and intensity are optional. Business name, type, location and voice come from the connected Klynx account. Returns a public URL for the enhanced image, the captions with hashtags and post ids, alt text, the intensity used, and the posts remaining in the plan allowance. Uses one post per platform and one AI enhancement 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. Klynx does not supply, search for or generate images, and it does not generate people or anything else in the scene; it only enhances the image the user provides. It only creates drafts in the Klynx account: it does not publish, schedule or post anything. To post its Facebook or Instagram draft, use klynx_preview_publish, then klynx_publish_now or klynx_schedule_post once the user approves.

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": "klynx_create_post_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
lengthNoOptional. Caption length for every platform: short, medium or long. By default Instagram, Facebook, TikTok and LinkedIn are medium.
subjectNoOptional note on what the photo shows (up to 200 characters are used).
image_urlNohttps URL of a JPEG, PNG or WebP photo, up to 20MB. Send this or upload_id, not both.
intensityNoOptional strength of the colour and light enhancement. Defaults to medium.
platformsNoPlatforms to write for. Any of instagram, facebook, tiktok, linkedin. Defaults to all four.
upload_idNoupload_id from klynx_request_photo_upload, once the photo has been uploaded. Send this or image_url, not both.
idempotency_keyNoOptional key that makes a retry safe: a key already used is never charged or run twice.

Output Schema

NameRequiredDescriptionDefault
pack_idYesThe id of this post pack.
alt_textYes
captionsYes
post_idsYesThe saved posts in the Klynx account, in caption order.
image_urlYesThe same URL as enhanced_image_url.
intensityYes
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.
enhanced_image_urlYesPublic URL of the enhanced photo.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well past the annotations: discloses that upscaling below 1280px can add fine detail, that each platform costs one post and one AI enhancement from the plan allowance, that an uncovered job is refused with plan_allowance_exhausted before any work, that failures consume nothing, and that free-plan captions carry a 'Made with klynx.ai' line. It also states the output is drafts only. The annotation idempotentHint=false is not contradicted — the description explains that idempotency_key is an opt-in retry-safety mechanism.

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 trigger condition and organized from what it does → constraints → billing → limits → what it does not do → next steps. The content mostly earns its place, but a single ~300-word paragraph is dense; splitting billing/allowance rules into their own sentences would improve scanability.

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 high-complexity, billable, multi-platform generation tool the description covers inputs, plan-allowance accounting, failure and refusal semantics, watermarking, and the follow-on publishing path. Since an output schema exists, it need not detail return fields, yet it still flags the enhanced-image URL, captions with post ids, alt text, and remaining allowance.

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 baseline is 3, but the description adds meaning the schema lacks: a minimum 800px longest edge for the input image, the https/upload_id mutual exclusivity with its provenance, and the fact that platforms/subject/length/intensity are optional. It does not restate the enum values, which the schema already handles.

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?

Opens with a concrete trigger plus verb+resource: enhance a user-supplied photo and write one caption per platform. It immediately bounds the scope ('only enhances the image the user provides', 'never invents anything') and distinguishes itself from klynx_write_captions by stating enhancement is only available bundled with captions.

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?

Gives an explicit when-to-use condition (user has a photo chosen for a business post and wants it post-ready) and names the alternates by name: klynx_request_photo_upload as the source of upload_id, and klynx_preview_publish → klynx_publish_now / klynx_schedule_post for the publish step it does not perform. It also carves out what it does not do (no image sourcing, no publishing) so the agent can route elsewhere.

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