Skip to main content
Glama
Sign In

Nextmail

by sh.nextmail
OverviewDiscussionsAdmin

Set brand image

setBrandImage
Destructive

Set one of the brand images of this workspace from an image in Files, replacing the one there was: the mark (a square icon), the logo, the logo for dark mode, or the photo behind the sign-in page of its web app address. Setting the sign-in photo also switches the sign-in page to it. The image is fitted and stored as WebP; it can start from up to 100MB. Pass crop to keep only part of it.

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": {
      "variant": "<variant>",
      "fileId": "<fileId>"
    },
    "name": "setBrandImage"
  }
}

Input Schema

NameRequiredDescriptionDefault
cropNoThe part of the image to keep, each value a fraction of the whole from 0 to 1: x and y are its left and top edges, width and height its size. Leave it out to keep the whole image.
fileIdYesThe fileId of an image in Files: one the user attached in this chat, or one listFiles found.
variantYesWhich image: mark, wordmark, wordmark-dark, login-background. mark is the square icon, wordmark the logo, wordmark-dark the logo for dark mode, and login-background the photo behind the sign-in page of the web app address.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true; the description corroborates by saying it replaces the existing image, and then adds genuinely new behavior: setting the sign-in photo also switches the sign-in page to it, the image is fitted and re-encoded as WebP, and the source can be up to 100MB. It stops short of covering permissions or how to undo, which is why it isn't a 5.

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?

Four sentences that are dense with usable information, front-loaded with the action and the variant list. Phrasing like 'replacing the one there was' is slightly clumsy and the variant list appears both here and in the schema, costing a bit of tightness.

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, no-output-schema mutation, the description covers the side effects, the storage format, the source constraints, and the crop option, which is close to what an agent needs. The remaining gap is that it never says what the call returns (e.g. the new image URL or updated branding), which matters since there is no output schema.

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 on top: it constrains fileId to images living in Files and gives a 100MB source-size limit that the schema does not express, plus the intent of crop ('keep only part of it'). The enum semantics it repeats are already in the schema, so it does not rise to a 5.

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 ('Set one of the brand images of this workspace') and enumerates all four variants with their meaning (mark, wordmark, wordmark-dark, login-background). The 'brand images of this workspace' scoping also separates it from look-alikes such as setDomainLogo, setProfilePhoto, and setContactPhoto without needing 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 Guidelines3/5

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

The description implies usage by explaining what the variants are and that the source is an image in Files, but it never states when to pick this tool over siblings like updateBranding or removeBrandImage, nor any prerequisites (e.g. that the file must already exist or come from listFiles).

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

All Nextmail toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources