Skip to main content
Glama

ask_otto

Send a plain-language question to Otto and get an answer via an A2A agent or Moveworks assistant. Use it to reach ServiceNow AI assistants without writing API calls.

Instructions

Send a plain-language request to Otto and return the answer. Two routes: (1) a2a, which sends it over A2A to an AI agent on the instance: the agent argument, else NOWAIKIT_OTTO_AGENT, else the A2A-exposed agent that looks like an orchestrator or assistant. This needs an OAuth (JWT) sign-in with the a2aauthscope scope and synchronous external agent mode. (2) moveworks, the Moveworks Conversations API (EmployeeWorks assistant), used when MOVEWORKS_API_BASE, MOVEWORKS_API_TOKEN (a user bearer from /oauth/v1/token) and MOVEWORKS_ASSISTANT_NAME are set. The moveworks route is a configured route, not verified against a live tenant. route=auto picks a2a when an agent is named or NOWAIKIT_OTTO_AGENT is set, else moveworks when configured, else a2a. Agents act with their 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": {
      "message": "<message>"
    },
    "name": "ask_otto"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentNoa2a: agent sys_id or name to send to
routeNoWhich route (default auto)
messageYesWhat to ask Otto
task_idNoa2a: answer an agent that asked for more input
context_idNoa2a: continue an earlier conversation
wait_secondsNoHow long to wait for the answer (default 120)
conversation_idNomoveworks: continue an earlier conversation (conv_...)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing auth requirements (OAuth JWT with a2aauthscope scope, synchronous external agent mode), the unreliable status of the moveworks route ('not verified against a live tenant'), fallback agent resolution, and the hard requirement that WRITE_ENABLED=true because agents invoke their own tools. These are exactly the preconditions an agent needs before calling a non-idempotent, open-world tool.

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?

Purpose is front-loaded in sentence one and the route detail follows in priority order. The middle sentence is heavily nested with parentheticals and parenthesized env-var lists, which makes it dense to parse, though nearly every clause carries operational information.

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?

No output schema exists, yet the description only says it 'returns the answer' without indicating shape or what happens on a wait_seconds timeout, which is a real gap for a 120-second synchronous call. Auth, routing, and write-enable requirements are otherwise complete for a seven-parameter tool.

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 the baseline is 3, but the description adds real meaning: the agent fallback chain for the unnamed case, the resolution semantics of route=auto, and which parameters belong to which route. It still does not explain the format of task_id/context_id/conversation_id beyond route tagging.

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 first sentence gives a specific verb, resource, and outcome ('Send a plain-language request to Otto and return the answer'), and the two-route breakdown makes clear this is the execution tool rather than the status/inspection siblings like get_otto_status. An agent can distinguish it without opening the 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 explicit routing conditions, including the exact auto-resolution order (named agent / NOWAIKIT_OTTO_AGENT -> a2a, else configured moveworks, else a2a) and the environment prerequisites for the moveworks route. It stops short of naming alternative sibling tools or stating when not to call this at all, so it is clear context rather than full when/when-not guidance.

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