Skip to main content
Glama

send

Delivers messages to agent sessions, rooms, or lists and returns delivery status—routed, queued, or held—so you know whether each recipient got it or is waiting.

Instructions

Send a message to name@device, #room, * or a list. Returns each recipient's status: routed (handed to a live session), queued (that session is offline; the relay keeps it 24 h), or held (that session's loop breaker holds this device's messages; held_note says until when). None means delivered or read; history shows receipts that come back (delivered, or held on that device). notify_when_idle: one notice when each name@device next finishes a turn or ends (watching lists them; watch_note says what was not armed); with no text it only arms.

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": {
      "to": "<to>"
    },
    "name": "send"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesname@device, #room, *, or a list
textNo
reply_toNo
notify_when_idleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and largely succeeds: it discloses the three delivery statuses (routed/queued/held), the 24 h queue retention, the loop-breaker behavior with held_note, and receipt semantics via history. It omits auth requirements and any message size/rate limits, keeping it short of a 5.

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 action and addressing forms, and the dense parentheticals all carry real information rather than filler. It is readable but telegraphic, with heavy nested clauses that could be split into clearer sentences.

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 4-parameter, no-output-schema, no-annotation tool, the description covers return semantics in unusual depth. The remaining omission is reply_to plus any permission or size constraints, which would round it out.

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?

Schema coverage is 25%, so the description must compensate. It clarifies that text is optional ('with no text it only arms') and fully explains notify_when_idle, but it never explains reply_to, leaving one of four parameters with no semantic definition anywhere.

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') and enumerates the addressing forms (name@device, #room, *, list). It doesn't explicitly contrast with siblings like reply, ask, or send_file, so an agent must infer the split from names alone, but the core purpose is unambiguous.

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

Usage Guidelines3/5

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

Recipient formats and the notify_when_idle mode are described, giving implied guidance on how to call it. There is no explicit when-to-use-this-vs-alternatives guidance (e.g., reply vs send, or send_file for attachments), which is the main gap for a 10-sibling toolset.

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

Deploy Server

Other Tools