Skip to main content
Glama

New words for a post

new_words
Destructive

New words and hashtags for one draft post, written by Audora for the post's own idea, in the campaign's language or the one you name. Its picture or video stays as it is; nothing new is made. Replaces the post's words. feedback is the artist's note on what should change. 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. To write the words yourself, use update_post (free).

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": "new_words"
  }
}

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).
feedbackNoOptional, ≤ 2000 characters: what should change in the words, in the artist's own words.
post_languageNoOptional: write it in this language, which the post then keeps as its own. The campaign's own language makes the post follow the campaign again.
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. Changed1 schema field changed
    • changedInput schema / properties / post_language / enum
      Previous value: -[
      -  "en-US",
      -  "en-GB",
      -  "sv",
      -  "nb",
      -  "da",
      -  "fi",
      -  "is",
      -  "de",
      -  "nl",
      -  "fr",
      -  "es-ES",
      -  "es-419",
      -  "pt-BR",
      -  "pt-PT",
      -  "it",
      -  "zh-CN",
      -  "zh-TW",
      -  "ja",
      -  "ko"
      -]New value: +[
      +  "en-US",
      +  "en-GB",
      +  "sv",
      +  "nb",
      +  "da",
      +  "fi",
      +  "is",
      +  "de",
      +  "nl",
      +  "fr",
      +  "es-ES",
      +  "es-419",
      +  "pt-BR",
      +  "pt-PT",
      +  "it",
      +  "ig",
      +  "zh-CN",
      +  "zh-TW",
      +  "ja",
      +  "ko"
      +]
  2. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false; the description adds meaningful context beyond them: the existing picture or video is preserved, nothing new is generated, the post's words are replaced, feedback carries the artist's intent, and each call costs 1 credit with the price revealed only by a dry run. It stops short of saying whether the previous wording can be recovered after replacement, which matters for a destructive write. It does not contradict the destructive annotation — it reinforces it.

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-loads what the tool produces, then the media/language constraints, then the cost-and-confirmation procedure, then the alternative. Dense but nearly every clause carries decision-relevant information; the 'feedback is the artist's note' sentence slightly restates the schema's own wording.

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 destructive, credit-costing rewrite with no output schema, the definition covers cost, permission, ordering, media preservation, and language persistence. The main omission is what the agent gets back after a successful or dry run call, and whether prior wording is recoverable.

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: feedback is framed as the artist's note on what should change, and post_language is described as the language the post then keeps as its own. The credit/permission note explains why dry_run and confirm_cost_credits are used together, which the schema alone states only individually.

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 (writes/replaces the words and hashtags) on a specific resource (one draft post), names the author (Audora) and the constraint that media is untouched, and explicitly distinguishes itself from update_post (free, self-written). An agent can separate this from 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 Guidelines5/5

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

Gives an explicit ordered workflow: dry_run first, tell the artist the price, then confirm_cost_credits for the real call. It also names the alternative and its tradeoff — 'To write the words yourself, use update_post (free)' — so the when-not-this path is covered.

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