CRM Connector

Change an AI agent's settings

update_ai_agent

DestructiveIdempotent

AI Agents (inside one system): Use when the customer asks to change what one AI agent may do: which record types it reads or reads and writes, which groups of actions are switched on (for example when a tool answered that a group is switched off), read only, or pausing and resuming it. Call it first without confirm: it answers the agent's settings now and what would change, and saves nothing. Show that to the customer, and call again with the same settings and confirm true only after they said yes. Only an Owner or Administrator can change settings. Not for removing an agent or switching a saved one on (both in CRM Connector), and not for automations (use propose_automation and set_automation_status).

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": {
      "system": "<system>"
    },
    "name": "update_ai_agent"
  }
}

Input Schema

Name	Required	Description
`status`	No	Optional: paused to stop the agent until it is resumed, active to resume it.
`system`	Yes	Which AI agent: the system's id from get_ai_agent_options, or the name of the system or its connection. Ask the person which AI agent they mean unless they named it in this conversation; never pick one yourself.
`confirm`	No	Leave it out to review the change. True saves it, only after the customer said yes to that review in this conversation.
`read_only`	No	Optional: true to let the agent only read until it is switched off again, false to let it change records again.
`record_types`	No	Optional: record types to change, as get_ai_agent_options lists them, each to off, read or read_write. Types left out stay as they are.
`turn_on_actions`	No	Optional: names of groups of actions to switch on, as this tool or get_ai_agent_options lists them. A group that is on already takes on the actions added to it since.
`turn_off_actions`	No	Optional: names of groups of actions to switch off.

Output Schema

Name	Required	Description	Default
`id`	Yes
`saved`	Yes
`notice`	No
`status`	Yes
`system`	Yes
`changes`	Yes
`package`	Yes
`readOnly`	Yes
`notChanged`	Yes
`systemName`	Yes
`recordTypes`	Yes
`settingsUrl`	Yes
`actionGroups`	Yes
`connectionName`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say the call is non-read-only, destructive, and idempotent; the description adds that the first call saves nothing and returns current settings plus a diff, and that a second call with confirm=true is what actually applies changes. It also discloses the Owner/Administrator authorization requirement, which annotations do not carry.

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 purpose, then the confirm workflow, then permissions, then exclusions — a logical order. It is dense with parentheticals and long clauses, but each sentence carries distinct information, so the length is justified rather than padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, multi-parameter mutation with a preview/apply cycle, the description covers what changes, what the preview returns, who may call it, and which siblings handle adjacent jobs. An output schema exists, so return-value detail is correctly left out.

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 the intent semantics of confirm ('call again with the same settings and confirm true only after they said yes'), which is more than the schema's terse default-false note. It does not add much about record_types or action-group naming beyond referring to get_ai_agent_options.

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?

States a specific verb and resource ('change what one AI agent may do') and immediately enumerates the scope: record types it reads/writes, action groups, read-only, pause/resume. It explicitly separates itself from CRM Connector removal/toggling and from automation siblings.

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

Usage Guidelines5/5

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

Gives concrete triggers ('when a tool answered that a group is switched off'), names the preferred alternative for automations (propose_automation and set_automation_status), and excludes out-of-scope work. The two-step confirm protocol is spelled out as a when-to-call sequence.

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

All CRM Connector tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?