Skip to main content
Glama

Define per-contact lines for a campaign

argorant_set_campaign_personalization
Destructive

Set up a campaign's personal lines, 1 to 5 {{custom_...}} variables, each with one instruction for writing the line and one fallback that reads well for anyone. Use it once before writing lines. To save the written lines use argorant_set_lead_custom_fields, and to see progress and the next contacts use argorant_campaign_personalization_status. It replaces the campaign's earlier setup, and every contact without their own line gets the fallback at once, so the emails can use the variables and the campaign can launch at any time. The result is plain data with the saved variables, how many contacts have the fallback, and playbook, the written method for writing the lines, as plain data. Next, look up facts for each contact and never invent anything, show the user 5 example lines, and after their yes write the rest. Instructions take up to 4,000 characters, lines 20 to 300 characters (max_length, 150 by default) and the template up to 10,000 characters. More in the docs at https://docs.argorant.com/docs/agents/tools#campaigns

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": {
      "campaign_id": "<campaign_id>",
      "variables": "<variables>"
    },
    "name": "argorant_set_campaign_personalization"
  }
}

Input Schema

NameRequiredDescriptionDefault
templateNoOptional email text the line goes into, up to 10,000 characters.
variablesYes1 to 5 variables, as [{name, instruction, fallback, max_length?, case?}]. name starts with custom_, such as custom_lead_types. instruction says what the line says, its length and style, with 2 or 3 examples. fallback is a line that reads well for anyone. case auto (the default) lowercases the first letter of a line used in the middle of a sentence and keeps a line that starts a sentence as written; sentence_middle always lowercases it and as_is keeps every line exactly as written. Acronyms, names, brands and places always stay as written.
allow_linksNofalse (the default, recommended) keeps links out of the lines.
campaign_idYesThe campaign's id, from argorant_list_campaigns.
extra_columnsNoContact or company fields worth reading for the lines, such as industry, city or title.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the destructiveHint=true annotation, the description explains exactly what is replaced: the campaign's earlier setup. It also discloses that contacts without their own line immediately get the fallback, meaning emails can use variables and launch right away. This is strong disclosure of a destructive mutation's side effects.

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 description is information-dense and mostly front-loaded, but it is long and includes some redundancy, especially the repeated phrase 'as plain data.' The sequencing is logical, moving from purpose to alternatives, side effects, results, workflow, and limits.

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 campaign mutation, the description covers prerequisites, replacement behavior, fallback effects, result shape, character limits, and next steps. With an output schema present, it does not need to over-explain return values, yet it still gives enough context to use the tool safely.

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 useful limits not present in the schema: instructions up to 4,000 characters, lines 20 to 300 characters, and max_length defaulting to 150. It also clarifies that variables are {{custom_...}} placeholders with one instruction and one fallback.

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 description opens with a specific verb and resource: setting up a campaign's personal lines with 1 to 5 {{custom_...}} variables. It distinguishes this tool from neighboring tools by naming argorant_set_lead_custom_fields for saving written lines and argorant_campaign_personalization_status for progress.

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?

It explicitly says to use this once before writing lines, names the alternative tools for saving lines and checking progress, and gives a downstream workflow: look up facts, show five example lines, then write the rest after user approval.

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.