Skip to main content
Glama

messages_send_media

Destructive

Send one message carrying one or more local files to a Kalagh channel, chat, contact, or phone number. Add captions or recipient-visible filenames and confirm before delivery.

Instructions

Send a message carrying one or more uploaded files Reaches other people on the platform, deletes, or redirects data — say exactly what will happen and get the user’s confirmation first. (POST /api/kalagh/messages/send-media · gRPC SendMedia)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filesYesThe attachments, ONE message carrying all of them. Each is a file on the machine running this MCP server.
chatIdNo
captionNo
metadataNoPer-platform side channel (`MessageContent.metadata`), e.g. {"email":{"to":["a@b.c"],"subject":"Hi"}}.
usernameNo
channelIdYes
contactIdNo
messageTypeNoMessageType — 2 Image, 4 Audio, 5 Voice, 6 Video, 7 Document. Derived from the file when absent.
phoneNumberNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description's warning about reaching other people is consistent but largely redundant. The generic 'deletes, or redirects data' phrasing does not describe this tool's actual side effects (single multi-file message, recipient visibility, file handling), so it adds only modest context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose well, but the second sentence is boilerplate safety text that could apply to any tool, and the trailing endpoint/gRPC note adds no decision value for an agent. Roughly half the content earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A destructive, open-world mutation with 9 params, nested objects, no output schema and low schema coverage needs far more: whether files are uploaded (not linked), recipient targeting rules among the many id-type params, and what the call returns. None of that is present.

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

Parameters2/5

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

With 9 parameters at only 33% schema coverage, the description is needed to compensate and does not. The only parameter-relevant content ('one or more uploaded files') merely restates the files array description, leaving channelId, caption, metadata, username, contactId, phoneNumber, messageType and chatId undescribed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Send a message carrying one or more uploaded files'), which distinguishes it from the text-oriented messages_send and the other send_* variants by emphasizing file attachments. It does not explicitly name the closest sibling, but the resource and payload are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

The only guidance is a generic caution ('reaches other people... get the user's confirmation first') rather than a when-to-use statement. It never contrasts this with messages_send, messages_reply, or the other send variants, so the agent must infer selection from scratch.

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