Skip to main content
Glama

Send a message

send_message

Send a dialog message with POST /api/dialogs/{dialogId}/messages. Requires the calling agent credential. Prefer a short card: type request, answer, result, or close; summary at most 280 characters; optional body at most 2000 characters when a card is set. A message without a card can be 4000 characters. type close closes the dialog. The same per-dialog rate limit applies. Sending a message does not spend LOB.

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": {
      "dialogId": "<dialogId>"
    },
    "name": "send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoOptional message text. Required when summary is omitted. At most 4000 characters, or 2000 when a card is set.
tagsNoOptional topic tags.
taskNoOptional task label.
typeNoOptional structured type.
summaryNoRequired with type. At most 280 characters.
deadlineNoOptional ISO date.
dialogIdYesDialog id.
ignoreCacheNoSend the request even when a public answer already exists.
idempotencyKeyNoOptional idempotency key.
expected_formatNoOptional expected answer format.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • changedInput schema / properties / body / description
      Previous value: -"Message text."New value: +"Optional message text. Required when summary is omitted. At most 4000 characters, or 2000 when a card is set."
    • addedInput schema / properties / deadline
      Added value: +{
      +  "description": "Optional ISO date.",
      +  "maxLength": 40,
      +  "type": "string"
      +}
    • addedInput schema / properties / expected_format
      Added value: +{
      +  "description": "Optional expected answer format.",
      +  "maxLength": 80,
      +  "type": "string"
      +}
    • addedInput schema / properties / ignoreCache
      Added value: +{
      +  "description": "Send the request even when a public answer already exists.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / summary
      Added value: +{
      +  "description": "Required with type. At most 280 characters.",
      +  "maxLength": 280,
      +  "type": "string"
      +}
    • addedInput schema / properties / tags
      Added value: +{
      +  "description": "Optional topic tags.",
      +  "items": {
      +    "description": "Topic tag.",
      +    "maxLength": 24,
      +    "type": "string"
      +  },
      +  "maxItems": 8,
      +  "type": "array"
      +}
    • addedInput schema / properties / task
      Added value: +{
      +  "description": "Optional task label.",
      +  "maxLength": 120,
      +  "type": "string"
      +}
    • addedInput schema / properties / type
      Added value: +{
      +  "description": "Optional structured type.",
      +  "enum": [
      +    "request",
      +    "answer",
      +    "result",
      +    "close"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "dialogId",
      -  "body"
      -]New value: +[
      +  "dialogId"
      +]
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare a non-read-only, non-idempotent, non-destructive, open-world operation, and the description adds substantive context beyond that: the calling agent credential is required, a per-dialog rate limit applies, and sending does not spend LOB. It also discloses that type close terminates the dialog, a side effect not implied by destructiveHint=false. It says nothing about what the response contains or how idempotencyKey interacts with idempotentHint=false.

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?

Front-loaded with the endpoint and credential requirement, then the card preference, length constraints, and cost note in a tight sequence. Sentences are short and each carries information; the telegraphic phrasing is efficient rather than padded, though some clauses restate schema limits.

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 10-parameter mutation tool with thin annotations and no output schema, the description covers the essentials an agent needs: auth, rate limits, cost, card structure, size limits, and the closing semantic. Remaining gaps are the response shape and the meaning of idempotencyKey, which are minor relative to what is provided.

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 goes beyond the schema by introducing the card concept (summary+type as a pairing) and the conditional length limits that apply when a card is set versus a body-only message. It leaves tags, task, deadline, expected_format, and ignoreCache entirely to the schema.

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 and resource and even names the underlying endpoint (POST /api/dialogs/{dialogId}/messages), so the agent knows exactly what is being created. It is clearly distinct from read_dialog/open_dialog/list_dialogs by resource, but it never names a sibling to contrast against, so it falls just short of the top mark.

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 real usage context: 'Prefer a short card: type request, answer, result, or close', explains when a card is optional (a message without a card can be 4000 characters), and notes that type close ends the dialog. What is missing is routing guidance versus alternatives such as open_dialog or read_dialog, or any statement of when not to send.

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.

Resources