Skip to main content
Glama

sendbird

by io.usefulapi

Send a message

sendbird_send_message
Destructive

MUTATES Sendbird data: sends a message into a channel as a user (MESG) or as an admin (ADMM). File/multipart messages are not supported. Platform API: POST /{channel_type}/{channel_url}/messages.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNoAdditional structured data as a string (often JSON).
messageYesThe message text.
user_idNoSender user id. REQUIRED when message_type is MESG.
is_silentNoIf true, does not update channel's last message / unread counts.
send_pushNoWhether to send push notifications. Default true.
channel_urlYesChannel URL (percent-encoded automatically).
custom_typeNoCustom type tag for the message.
channel_typeYesChannel type: group_channels (member-based) or open_channels (public, participant-based).
mention_typeNoMention scope: specific users or the whole channel.
message_typeNoMESG (user text, default) or ADMM (admin message, no sender).
mentioned_user_idsNoUser ids to mention (when mention_type=users).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

The description explicitly leads with 'MUTATES', reinforcing the destructiveHint annotation, and adds behavioral detail beyond the schema: file/multipart payloads are unsupported and the operation maps to POST /{channel_type}/{channel_url}/messages. It does not discuss delivery/push consequences, but the schema already documents silent and push controls.

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?

Three sentences, each earning its place: mutation and function, the unsupported multipart limitation, and the API endpoint. The key MUTATES signal is front-loaded.

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 an 11-parameter mutation tool with a fully documented schema and destructiveHint, the description plus schema is largely sufficient. The main gap is the lack of any hint about the response/return value, since no output schema is provided.

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?

The input schema has 100% description coverage, so the description does not need to re-document parameters. It adds little semantic value beyond the schema—'MESG/ADMM' already appears in the message_type property—so baseline 3 is appropriate.

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 description uses a specific verb ('sends') with a clear resource ('a message into a channel') and distinguishes the two modes (MESG user, ADMM admin). It states the exact API endpoint, making it unambiguous and distinct from sibling read tools like sendbird_list_messages.

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?

It clearly marks the operation as a mutation and gives a concrete exclusion ('File/multipart messages are not supported'), so an agent knows when not to use it. However, it does not explicitly name alternatives or spell out when to prefer a sibling such as sendbird_request for unsupported payloads.

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

All sendbird toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation5/5

Each tool maps to a distinct resource-action pair (users, group/open channels, members, messages), and the get/list/create/update/send verbs keep boundaries clear. The raw GET escape hatch is explicitly limited to unwrapped paths, so it does not create meaningful overlap.

Naming Consistency5/5

All tools follow the predictable sendbird_<verb>_<resource> snake_case pattern, with consistent verbs like create, get, list, update, and send. The generic sendbird_request is a deliberate exception rather than a naming inconsistency.

Tool Count5/5

14 tools is within the ideal range and each tool covers a coherent piece of Sendbird's chat platform: users, channels, members, messages, and a raw GET fallback. There are no redundant or filler tools.

Completeness3/5

The set covers common read/list flows and some mutations, but lifecycle coverage has notable gaps: group channels can be created and read but not updated/deleted, messages can be sent and listed but not updated/deleted, and users have no delete operation. The raw GET tool is read-only and cannot compensate for these missing write operations.

Resources