Mentio

Create automation

create_automation

Create an automation: a name, a filter in the vocabulary of search_mentions (as create_view takes it; empty acts on every mention) and actions: addLabels (up to 10) and/or assigneeId (a member, assigned only when nobody is). It runs on every NEW mention its filter selects, right after scoring and before delivery, so an alert rule on labels can route what it labels ("buy intent on LinkedIn" -> label hot-lead -> an alert rule on labels [hot-lead] to the sales channel). Existing mentions are not touched: use update_mentions for those. At most 25 per workspace; they run oldest first, a later one seeing labels an earlier one added.

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": {
      "name": "<name>",
      "actions": "<actions>"
    },
    "name": "create_automation"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Unique per workspace, case-insensitive.
`filter`	No	Which new mentions it acts on; empty acts on every one.
`actions`	Yes	What to do to each mention the filter selects; at least one action.
`enabled`	No	false saves it without running it.
`idempotencyKey`	No	Optional. A unique value (a UUID) for this call: 1 to 255 visible ASCII characters, no spaces. Calling again with the same key and the same input within 24 hours returns the first result instead of doing it twice.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly=false, destructive=false, openWorld=false, so the description's job is to add lifecycle context, which it does well: execution timing after scoring and before delivery, ordering (oldest first), visibility of earlier automations' labels, and the 25-per-workspace cap. It does not state how addLabels interacts with an at-capacity mention (the 20-label ceiling lives only in the schema), which keeps it short of a 5.

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 the shape of the call, then the runtime semantics, then the exclusion. Dense but nearly every clause carries information; the alert-rule example is the one indulgence, justified because routing behavior is otherwise non-obvious.

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 tool with a deeply nested filter object and no output schema, the description covers execution semantics and limits thoroughly. The notable gap is what a successful call returns (an automation id?), which the agent would need for a follow-up get_automation or update_automation call.

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 baseline is 3; the description adds meaning by tying `filter` to the search_mentions/create_view vocabulary and clarifying that an empty filter acts on everything. It also restates the addLabels cap and the conditional nature of assigneeId, though both are already in the schema, so the lift is moderate rather than substantial.

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?

Opens with a specific verb and resource ("Create an automation") and immediately enumerates the three things that define it: name, filter, actions. It distinguishes this from update_automation and update_mentions by scope (new mentions only) rather than leaving the agent to guess.

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?

Explicitly routes the agent away from this tool for existing mentions ("Existing mentions are not touched: use update_mentions for those") and explains the intended composition with create_alert, including a concrete worked example. The filter vocabulary is anchored to a named sibling (search_mentions / create_view) so the agent knows where to reuse filter knowledge.

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

All Mentio 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?