Skip to main content
Glama

Agent messenger

agent_message
Read-only

Send live instructions to another active agent or list active agents and their tasks, enabling coordination across sessions or PCs.

Instructions

Send a live message/instruction to another working agent connected to this ZeroIDE MCP server (for example, when coordinating from another PC or another session), or list currently active agents and their tasks (action: 'list_agents'). When action: 'send' is used, if the target agent is currently executing run_command, its command is immediately backgrounded into a job_id (or stopped if stopCommand: true) and your message is delivered in <50ms; otherwise the target agent's very next tool call pauses at the gate with your message.

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": "agent_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoTarget agent name/id (from list_agents) or '*' for all active agents.
fromNoYour agent name/identifier.
noteNoShort human-readable explanation (1 line, in the user's language) of what you are about to do and why. Shown to the user on the approval card. Always provide when calling mutating tools.
textNoMessage or instruction to deliver to the target agent.
agentNoShort consistent identifier or display name of this agent (e.g. 'Claude · Лендинг', 'Тесты', 'Мой агент'). Used to separate tasks and route tray messages when multiple agents work in parallel.
actionNo
stopCommandNoIf true and the target agent is currently running a command, terminate that command immediately instead of moving it to a background job_id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior2/5

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

The description is unusually rich about delivery mechanics: under 50ms delivery, an in-flight `run_command` being backgrounded into a `job_id`, and commands being terminated when `stopCommand: true`. But those are state-changing effects on another agent's execution, while annotations declare readOnlyHint=true and destructiveHint=false; the description therefore contradicts the declared safety profile. That contradiction is the dominant issue here, though the delivery-latency and gating detail is genuinely valuable context.

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?

The core capability and the two actions are front-loaded, and every clause carries operational information rather than filler. It is dense — one long sentence with nested parentheses and backticked literals — which slightly slows parsing, but nothing could be cut without losing real meaning.

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 7-parameter, dual-mode tool with no output schema, the description covers the mode switch, delivery timing, and the side effect on a target's running command — enough to invoke it correctly. The gap is that `list_agents` results are never described (what fields identify an agent for `to`), which matters precisely because there is no output schema.

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 already 86%, so the baseline is 3; the description earns above that by explaining the two `action` values and the branching semantics of `stopCommand: true` (terminate vs. move to a background job) that the schema only states tersely. It says nothing about `to: '*'` broadcast or the `from`/`agent` identity parameters beyond what the schema already documents.

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 names a specific verb and resource — send a live message/instruction to *another working agent* on this MCP server — and explicitly covers the second mode (list currently active agents and their tasks). The phrase 'another working agent' plus the 'from another PC or another session' framing separates it cleanly from user_message and from run_command without needing either schema.

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 gives a concrete when-to-use condition (cross-PC / cross-session coordination) and tells the agent to use `action: 'list_agents'` to discover targets before sending, which is real routing guidance. It stops short of stating when NOT to use it — e.g. that user-facing notifications belong in user_message rather than here — so the agent must infer the boundary from 'another working agent'.

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