Skip to main content
Glama

sn_a2a_send_message

Sends a message to a ServiceNow AI agent over A2A and returns its reply or pending task; reuse context_id or task_id to continue the conversation. Requires WRITE_ENABLED.

Instructions

Send a message to a ServiceNow AI agent over A2A and return its reply (or the task when it needs more input or runs async). Pass context_id / task_id from a previous reply to continue the conversation. The agent acts with its own tools, so this REQUIRES WRITE_ENABLED=true.

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": {
      "agent": "<agent>",
      "message": "<message>"
    },
    "name": "sn_a2a_send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYesAgent sys_id or name
messageYesWhat to ask the agent
task_idNoAnswer an agent that asked for more input
context_idNoContinue an earlier conversation
wait_secondsNoHow long to wait for an async agent to finish (default 120, max 600; 0 returns the task immediately)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly=false, openWorld=true and non-idempotent, and the description adds the causal explanation: the remote agent acts with its own tools, which is why write access is required. It also discloses the return branching (reply vs. task) and async handling via wait_seconds. It does not address duplicate-send risks, failure modes, or latency/cost beyond the wait parameter.

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 tight sentences: purpose and return shape first, continuation guidance second, prerequisite last. No restated schema text, no filler, and the WRITE_ENABLED requirement is capitalized for salience.

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 5-parameter, open-world mutation tool with annotations but no output schema, the description covers purpose, return branching, continuation, async waiting, and the write prerequisite. Remaining gaps are error behavior and what happens when the target agent is missing or mid-task, which are secondary for a first correct invocation.

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 100%, so the schema already explains all five parameters. The description only adds relational meaning for context_id/task_id (that they come from a previous reply), which is a modest gain over the schema's own wording. Baseline 3 applies when the schema carries the parameter burden.

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?

Specific verb and resource: 'Send a message to a ServiceNow AI agent over A2A and return its reply'. The parenthetical about returning a task for async/input cases also implicitly separates it from poll-style siblings such as sn_a2a_get_task. It stops short of explicitly naming any sibling to route against, which keeps it from a 5.

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 concrete continuation guidance ('Pass context_id / task_id from a previous reply to continue the conversation') and a hard prerequisite ('REQUIRES WRITE_ENABLED=true'). It does not state when not to use this tool or name an alternative (e.g., listing agents first), so it is clear context without exclusions.

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