StealAds

Create a brand

create_brand

Creates a brand from the details supplied and returns it with its brand id. kind brand (default) needs name, industry, primaryColor, toneOfVoice and targetAudience; kind research needs only a name and suits competitor research, with details to add before making ads. Does not read the website and spends no credits. The plan's brand allowance applies.

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": {
      "name": "<name>"
    },
    "name": "create_brand"
  }
}

Input Schema

Name	Required	Description
`kind`	No	brand (default) is a full brand for making ads and needs industry, primaryColor, toneOfVoice and targetAudience. research needs only a name and suits competitor research; brand details are added before making ads.
`name`	Yes	Brand name, up to 200 characters.
`industry`	No	Industry or category the brand sells in, in plain words, e.g. skincare.
`websiteUrl`	No	Brand website as a full URL. Stored only; the site is not read or crawled.
`toneOfVoice`	No	How the brand sounds in ad copy, e.g. warm, direct, no jargon. Up to 2,000 characters.
`primaryColor`	No	Primary brand color as a six-digit hex value, such as #336699.
`targetAudience`	No	Who the brand sells to and what they need. Up to 2,000 characters.

Output Schema

Name	Required	Description	Default
`brand`	No	Accessible brand details.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 10, 2026

changedInput schema / properties / industry / description

Previous value: -"Industry the brand operates in."New value: +"Industry or category the brand sells in, in plain words, e.g. skincare."

changedInput schema / properties / kind / description

Previous value: -"research needs only a name and does not scrape a website; add brand details before making ads."New value: +"brand (default) is a full brand for making ads and needs industry, primaryColor, toneOfVoice and targetAudience. research needs only a name and suits competitor research; brand details are added before making ads."

changedInput schema / properties / name / description

Previous value: -"Name of this brand or collection."New value: +"Brand name, up to 200 characters."

changedInput schema / properties / targetAudience / description

Previous value: -"People the brand wants to reach and their needs."New value: +"Who the brand sells to and what they need. Up to 2,000 characters."

changedInput schema / properties / toneOfVoice / description

Previous value: -"How the brand should sound in ad copy."New value: +"How the brand sounds in ad copy, e.g. warm, direct, no jargon. Up to 2,000 characters."

changedInput schema / properties / websiteUrl / description

Previous value: -"Brand website URL; supplying it does not crawl the site."New value: +"Brand website as a full URL. Stored only; the site is not read or crawled."

First observedNov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Adds real behavior beyond the annotations: the website is stored but not read or crawled, no credits are spent, and the plan's brand allowance applies — none of which is derivable from readOnlyHint=false, idempotentHint=false, or the other hints. It stops short of explaining what happens when the allowance is exhausted or what a duplicate name does.

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 the action and return value, then the kind split, then the side-effect caveats — a sensible ordering. Two dense sentences with no filler, though some of the kind/field list duplicates schema text that could be trimmed.

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?

An output schema exists, so return values need no explanation, and the description covers the two creation modes, the no-credits/no-crawl behavior, and the quota constraint. Remaining gaps are edge-case behaviors (duplicate names, allowance exhaustion) rather than anything needed to call it correctly.

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 coverage is 100%, so all seven parameters are already documented, and the description's statement of which fields each kind needs largely restates the kind enum's own description. The conditional-requirement framing (only name is schema-required) is helpful reinforcement, but adds little genuinely new meaning beyond 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 ("Creates a brand ... returns it with its brand id") and immediately divides the operation into two named kinds (brand vs research) with their distinct inputs and purposes. An agent can tell exactly what is produced 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 selection guidance between the two modes: research "suits competitor research, with details to add before making ads", while brand is the default for making ads. It does not name any alternative tool (e.g. update_brand for existing brands), so the exclusion is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All StealAds tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.