Skip to main content
Glama

Touch up a post's photo

touch_up
Destructive

Touch up the artist's own photo on one draft picture post, as Promo's Touch up: cut to the post's shape and given light, contrast, warmth and color by Audora's own renderer. No AI: the pixels stay the artist's. Saved as a new picture in the Library and put on the post (and on the other draft pictures of its moment); the photo it was made from stays. For a photo of the artist's own, never a video post. Costs 1 credit (the dry run says the price); the real call needs the artist's spend permission. dry_run first, tell the artist the price, then confirm_cost_credits.

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": {
      "post_id": "<post_id>"
    },
    "name": "touch_up"
  }
}

Input Schema

NameRequiredDescriptionDefault
artistNoOnly when you are connected as a label: the roster artist this call is for — their artist_user_id from list_roster, or their exact artist name. Required for every artist tool on a label connection. Leave it out on an artist's own connection.
dry_runNoTrue to see the price, changing nothing. Do this first and tell the artist.
post_idYesThe post's id (post_id from get_campaign or promo_this_week).
idempotency_keyNoSend the same key if you retry, and the change happens once.
confirm_cost_creditsNoThe price a dry run quoted and you told the artist. Required for the real call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say readOnly=false, destructive=true, idempotent=false; the description goes well beyond that by disclosing that the source photo survives, that a new picture lands in the Library, and — critically — that the result is also applied to other draft pictures of the same moment, an unobvious side effect. It adds cost (1 credit), the spend-permission requirement, and a retry key, which the annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly ninety words, front-loaded with the action and its effect, then side effects, exclusions, and the required call sequence. Every clause carries information an agent would otherwise have to guess; nothing is redundant with the title or the annotations.

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?

No output schema exists, but the description covers what is produced (a new Library picture, applied to the post and its sibling drafts) and what is not (the original). With a credit cost and permission gate in play, this is everything an agent needs to call it safely and set expectations for the artist.

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 beyond the field docs: it ties dry_run and confirm_cost_credits into a required ordering where the confirmed number must be the price quoted to the artist. The artist/roster-connection nuance is left entirely to the schema.

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 ("Touch up the artist's own photo on one draft picture post") and immediately scopes it: shape-cropped, tone-adjusted by Audora's renderer, no AI. It also explicitly rules out a neighbouring case ("never a video post"), so an agent can distinguish this from generic post-editing siblings without opening the schema.

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?

Gives clear when-to-use conditions (artist's own photo, draft picture post) and a when-not (video posts, AI-generated content), plus an explicit call sequence: dry_run first, tell the artist the price, then confirm_cost_credits. It does not name a sibling tool to use instead for the excluded cases, so it stops just short of full routing guidance.

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