Skip to main content
Glama
whatsapp-cloud-mcp

whatsapp-cloud-mcp

Upload WhatsApp media

upload_media

Uploads a local or public HTTPS media file to WhatsApp and returns a media_id for reuse when sending media messages.

Instructions

Upload a media file to WhatsApp and get back a media_id you can reuse in send_media_message. Provide exactly one of file_path (a local file) or url (a remote file to fetch). file_path only works when the server is configured with WHATSAPP_UPLOAD_DIR and the file lives inside it; url must be a public https:// URL. The MIME type is inferred from the file extension when not given. Max 100MB.

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": "upload_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoPublic https:// URL to fetch and upload
file_pathNoPath to a local file inside WHATSAPP_UPLOAD_DIR to upload (disabled if that env is unset)
mime_typeNoMIME type, e.g. image/jpeg (inferred if omitted)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only declare openWorldHint and non-destructiveness; the description adds real behavioral context beyond that — the 100MB ceiling, the server-side env-configuration dependency that silently disables file_path, the public-URL requirement, and MIME inference from extension. It omits failure modes and whether uploads are scoped per-account, which keeps it out of 5 territory.

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?

Four sentences, front-loaded with purpose and payoff, then constraints in the order an agent would hit them. Every clause carries an actionable constraint; nothing is padding.

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 three-parameter upload tool with no output schema, it covers inputs, mutual exclusivity, size limit, configuration dependency, and the shape of the return value (media_id). An agent has everything needed to call it correctly on the first attempt.

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 baseline is 3, but the description adds a constraint the schema does not encode: exactly one of file_path or url (required is empty and there is no oneOf). It also clarifies the inference behavior for mime_type. That is genuine 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 (upload a media file to WhatsApp) and names the concrete outcome (a media_id reusable in send_media_message). This distinguishes it cleanly from the send_* siblings, which consume rather than create media.

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 explicit preconditions for each input mode: file_path requires WHATSAPP_UPLOAD_DIR and containment within it, url must be public https. It also tells the agent what to do next with the result (send_media_message). It stops short of stating when not to use it or naming alternative upload paths.

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