Skip to main content
Glama

sn_mcp_add_tool

Attach an existing tool definition or register a new tool from a Now Assist skill or Scripted REST operation on an MCP Server Console server, so MCP clients can call it.

Instructions

Add a tool to an MCP Server Console server. Either attach an existing tool definition (tool), or register a new one from a Now Assist / Otto skill (skill → sn_mcp_ai_skill_tool_definition, inputs copied from the skill's input attributes) or a Scripted REST operation (rest_operation → sn_mcp_scripted_rest_tool_definition, inputs you list). These are the two tool sources MCP Server Console offers; to expose a subflow, action, Knowledge Graph or AI Search, wrap it in a Now Assist skill or a Scripted REST operation first. REQUIRES WRITE_ENABLED=true and sn_mcp_server.admin.

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": {
      "server": "<server>"
    },
    "name": "sn_mcp_add_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoUnique definition name (default: label as snake_case)
toolNoExisting tool definition name or sys_id to attach (no new definition is created)
labelNoTool label MCP clients see as the tool name (default: skill or operation name)
skillNoNow Assist skill config (sn_nowassist_skill_config) sys_id or name, or the name of an existing skill tool to copy the skill from
inputsNoSkill: which skill inputs to expose (by attribute name; default all active ones); a value makes it a fixed (static) input. Scripted REST: the request fields the tool takes.
serverYesServer name, label or sys_id
descriptionNoWhat the tool does; MCP clients use it to decide when to call the tool (default: the skill or operation description)
rest_operationNoScripted REST resource (sys_ws_operation) sys_id, or "METHOD /api/..." / "/api/..." path

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the write/open-world profile is known; the description adds material value beyond that by disclosing the admin and WRITE_ENABLED prerequisites, that skill mode copies inputs from the skill's input attributes, and that a fixed value hides an input from MCP clients. It does not address idempotency or name-collision behavior on repeat calls, which the annotations flag as non-idempotent.

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?

Three sentences with the action front-loaded; the first sentence is a clean one-line summary and the alternatives follow. The second sentence is long and parenthetical-heavy, which slightly hurts scanability, but no sentence is filler.

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 an 8-parameter, non-idempotent mutation with no output schema, the description covers mode selection, prerequisites, and how inputs are derived, which is most of what an agent needs to call it correctly. It leaves the return value (e.g. the created definition's sys_id/name) and duplicate-name behavior unstated, which is the remaining gap given there is no output schema to fall back on.

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 mode-level meaning the schema cannot: `tool` vs `skill` vs `rest_operation` are alternative sources mapping to sn_mcp_ai_skill_tool_definition and sn_mcp_scripted_rest_tool_definition respectively, and skill inputs default to all active attributes. That mutual-exclusivity framing is genuinely beyond the per-property descriptions.

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?

Names a specific verb and resource ("Add a tool to an MCP Server Console server") and then enumerates the three concrete ways it can do so: attach an existing definition, derive one from a Now Assist/Otto skill, or derive one from a Scripted REST operation. An agent can distinguish this from sn_mcp_remove_tool, sn_mcp_list_tools and sn_mcp_call_tool purely from this text.

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?

Explicitly frames the choice between the two tool sources and states a when-not rule: to expose a subflow, action, Knowledge Graph or AI Search, wrap it in a Now Assist skill or Scripted REST operation first. It also states hard preconditions (WRITE_ENABLED=true, sn_mcp_server.admin). It does not reference sibling management tools (e.g. remove/list) for complementary operations, which keeps it short of a 5.

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