Skip to main content
Glama

Write each contact's personal line

argorant_set_lead_custom_fields
Destructive

Save the personal lines you wrote for a campaign's contacts, up to 5,000 per call, and add or remove contact tags. Use it after argorant_set_campaign_personalization and argorant_campaign_personalization_status; a finished file of up to 200,000 rows goes through the API or the command line instead, followed with argorant_personalization_import_status. Only the campaign's own variables are accepted. Write each line only from facts you looked up for that contact and never invent a detail, number, customer or claim; when the facts do not tell you, send keep_fallback: true. Before the first save, show the user 5 example lines inside their sentences and wait for a yes. Each line is plain text on one line, within the variable's max_length, with no links unless the campaign allows them. A saved line is never replaced unless overwrite is true; without it, a contact that has a line keeps it and is listed in kept_existing. The answer counts what was saved, refused with the reason, not found and still to write, and lists every replaced or cleared line in changes. Tags need no personalization setup; afterwards the remove, restore, move and list tools for campaign people can select by tag. 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>",
      "leads": "<leads>"
    },
    "name": "argorant_set_lead_custom_fields"
  }
}

Input Schema

NameRequiredDescriptionDefault
leadsYes1 to 5,000 contacts, as [{lead_id or email, values?, keep_fallback?, basis?, tags?, untag?}]. values maps each custom_ variable to its line, or to null with overwrite true to clear it. keep_fallback true keeps the fallback for a contact with no usable facts and takes them off the list; false puts them back on it. basis says in a few words where the fact came from, up to 200 characters. tags (a list, or tag as one text) and untag add and remove contact tags, saved in lower case; an entry with only tags needs no values.
overwriteNotrue replaces or clears lines the contacts already have. Leave it false (default) so saved lines are never replaced by accident.
campaign_idYesThe campaign's id, from argorant_list_campaigns.

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?

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: a saved line is never replaced unless overwrite is true, otherwise the contact is listed in kept_existing; the response reports saved, refused-with-reason, not-found and pending counts plus a changes list of replaced or cleared lines. The tagging side effect and its downstream effect on the remove/restore/move/list tools is also disclosed.

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?

Purpose and the sibling routing are front-loaded, and nearly every sentence carries operational weight (validation rules, overwrite semantics, response shape, doc link). It is a single dense block with no paragraph breaks, and the instruction about never inventing facts is more agent-behavior policy than tool definition, which slightly dilutes scanability.

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, batched write tool with an output schema and full annotation coverage, the description covers prerequisites, validation constraints, idempotency/overwrite behavior, response fields, and the tag side effect. Nothing an agent needs in order to invoke it correctly appears to be missing.

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 meaning the schema does not: lines must stay within the variable's max_length, no links unless allowed, only the campaign's own variables accepted, and tags are saved in lower case. It also explains the overwrite/kept_existing interaction, though the per-entry fields (values, basis, keep_fallback) are largely already documented in the schema itself.

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 opening sentence gives a specific verb and resource — saving personal lines for a campaign's contacts, capped at 5,000 per call — plus the secondary tag add/remove action. It distinguishes itself from the sibling that configures personalization (argorant_set_campaign_personalization) and from the bulk file path, so an agent can tell which tool writes lines versus which sets them up.

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?

Explicit sequencing is given: use after argorant_set_campaign_personalization and argorant_campaign_personalization_status, and route finished files of up to 200,000 rows to the API/CLI followed by argorant_personalization_import_status. It also states a required pre-flight workflow (show five example lines, wait for a yes) and that tags need no personalization setup, which is clear when-to-use and when-not guidance.

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.