Skip to main content
Glama

Add Automation Agent

addAutomationAgent

Add an agent to an automation on a team that is on the Automations workspace, with or without revisions — membership is not versioned. The agent must not already belong to another automation; on a team that changes its automations by revision it cannot be moved between them at all, because the revisions binding it are immutable. Adding an agent that is already a member succeeds unchanged. When the automation runs as the team, the agent's personal triggers and schedules are turned off, and the add fails with 409 if its live revision sends cases to a queue in an automation that runs as its members. An agent left behind by a deleted automation that ran as the team cannot join one that runs as its members (409). Adding to an automation that runs as the team also fails with 409 when a change in flight holds the rows the add has to update, such as the agent's personal triggers and schedules; that refusal changes nothing and the add can be retried.

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": {
      "automation_id": "<automation_id>",
      "agent_id": "<agent_id>"
    },
    "name": "addAutomationAgent"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_idYesAgent ID
automation_idYesAutomation ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior5/5

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

The description goes well beyond the annotations: it names the side effect (the agent's personal triggers and schedules are turned off when the automation runs as the team), enumerates concrete 409 failure conditions including a conflicting live revision, a deleted-automation leftover agent, and in-flight changes holding rows, and states that the failed add changes nothing and can be retried. That is unusually rich operational detail for a mutation tool. There is mild tension with idempotentHint=false via 'an agent that is already a member succeeds unchanged', but that describes one specific state rather than general idempotency, so it is not a contradiction.

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 action and its scope are front-loaded in the first sentence, and the remaining text is dense with distinct constraints rather than filler. A few clauses are wordy ('on a team that changes its automations by revision it cannot be moved between them at all'), and the final sentence restates the retryability already implied earlier. It is long but mostly earns its length.

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 two-parameter mutation with no output schema and non-destructive annotations, the description covers preconditions, side effects, failure modes, and retry behavior thoroughly. The remaining gap is that nothing indicates what a successful response contains or how to confirm the membership after the call. That is minor but keeps it from a 5.

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?

Both parameters are documented at 100% schema coverage and are bare UUID identifiers, so the schema already carries the burden. The description adds domain meaning about which entities are valid (agent from a team on the Automations workspace, target automation's run mode), but it adds no per-parameter syntax or format detail. The baseline 3 applies since there is little left for the description to contribute on parameters.

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?

The description opens with a specific verb+resource ('Add an agent to an automation') and scopes the precondition ('on a team that is on the Automations workspace'), so an agent knows exactly what is being created. It also distinguishes itself semantically from revision-based operations by stating 'membership is not versioned'. It never names the counterpart tool (removeAutomationAgent) or other membership siblings, so it stops short of 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?

It gives clear preconditions for calling: the agent must not already belong to another automation, and on revision-managed teams it cannot be moved between automations at all. It also states explicitly that adding an existing member succeeds unchanged, which tells the caller a repeat call is safe in that state. What it lacks is any explicit routing to alternative tools (removeAutomationAgent, moveAgent, createAutomation) when the caller's intent is different.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources