Skip to main content
Glama

Set or remove the company logo

set_company_logo
Destructive

Set or remove the company logo shown at the top of signature request emails, signing pages and signed PDFs (company admin only; uploading needs the Team or Business+ plan, removing works on any plan). PNG, JPG, WebP or GIF (no SVG), up to 300 KB; a wide logo about 400x100 px looks best. It replaces any existing logo and applies to documents already sent. Call it with no arguments to get upload_url, a private link that works for 30 minutes: if you can run commands, upload the file with curl -F file=@logo.png "<upload_url>" (this keeps the image out of the conversation); otherwise give the link to your human to open and choose the file, and ask them to tell you when the page says "Logo saved". curl gets a JSON reply saying the logo was saved. get_account user.company_logo only shows whether some logo is set, so it cannot confirm a replacement. Only pass content_base64 for small images you already have as bytes. Logos must be uploaded: links to images elsewhere are not accepted. remove: true deletes the logo. The logo is stored in private storage and shown through signed links that cannot be guessed, which md2sign only puts in the account, emails and documents of the company.

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": "set_company_logo"
  }
}

Input Schema

NameRequiredDescriptionDefault
removeNotrue deletes the current logo instead of uploading one.
api_keyNoAn md2sign API key. When given, this call uses that key's account even if the connection is signed in as someone else, so pass it on every call when your human has more than one md2sign account (for example two businesses). Also use it if your MCP client cannot send an "Authorization: Bearer <api_key>" header.
content_base64NoOptional. The image file's bytes, base64-encoded (a data: URL prefix is accepted). Prefer upload_url (call with no arguments) for anything but small images.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the annotations' destructiveHint, it discloses the consequences that matter: the logo replaces any existing one and applies retroactively to documents already sent, and removal deletes it. It also covers the upload_link's 30-minute private lifetime, format and size limits (no SVG, ≤300 KB), the curl invocation and its JSON reply, and that logos must be uploaded rather than referenced by external URL.

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?

Purpose and admin/plan constraints are front-loaded, and virtually every sentence carries unique information (limits, retroactivity, upload flow, privacy). It is a single dense block paragraph, though, and splitting the upload workflow into its own lines would make scanning easier without losing content.

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 zero-required-parameter mutation with no output schema, the description supplies everything an agent needs: what gets replaced or deleted, the two upload paths, the return value of the no-argument call, expected curl output, and the privacy model of the stored logo. No gap remains that would cause a wrong invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the baseline is 3, but the description goes further by describing the no-argument upload_url flow, the 30-minute expiry and how to consume the link (curl -F or human handoff), and by constraining content_base64 to small in-memory images. That operational meaning is not derivable from the schema field descriptions alone.

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?

The opening clause names a specific verb pair and resource: set or remove the company logo, and pins its exact surface (signature request emails, signing pages, signed PDFs). This is clearly distinct from siblings like update_account or get_account, which only read or set general account fields.

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?

It states prerequisites (company admin only; Team or Business+ for uploading, any plan for removing), gives the decision path for the two upload modes (no-argument call for upload_url vs. content_base64 for small images already in bytes), and explains when remove:true applies. It even warns that get_account's user.company_logo cannot confirm a replacement, heading off a sibling-tool misuse.

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.