Ballast - Cold Email

Write sequence

write_sequence

Write emails with AI from the offer profile. Drafts a whole sequence (mode sequence) or a new version of one variant (rewrite, shorter, angle), using only facts from the workspace's offer profile and lead fields. Results are saved as new variants and never overwrite existing text; an empty campaign gets the drafted steps. Each email is checked against the content checklist; anything still failing comes back in problems. Requires that the workspace's offer profile is configured in Ballast settings (or updated via update_offer_profile).

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": {
      "id": "<id>"
    },
    "name": "write_sequence"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes
`mode`	No	sequence = draft every step; rewrite, shorter, angle = a new version of one variant	sequence
`angle`	No	Optional angle or notes, e.g. 'lead with the cost of manual payroll'
`steps`	No	sequence mode: how many emails
`persona`	No	Optional target persona, e.g. 'operations managers at restaurant groups'
`variantId`	No	rewrite, shorter, angle: the variant to start from (required)

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Despite annotations already declaring non-destructive and non-read-only, the description adds real behavior: results are saved as new variants and never overwrite existing text, an empty campaign receives the drafted steps, and each email is validated against the content checklist with failures returned in 'problems'. The offer-profile prerequisite is an auth/config dependency the annotations cannot express.

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?

Four sentences, front-loaded with the purpose and then the mode behavior, then the non-overwrite guarantee, then the validation and prerequisite. Dense but each clause carries information; the parenthetical mode list is slightly redundant with the schema enum.

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?

With no output schema, the description does cover returns (new variants, drafted steps on empty campaigns, 'problems' for checklist failures) and the configuration prerequisite. The one real gap is that the required 'id' parameter is never explained — an agent has to guess whether it identifies a campaign or a variant — and the response shape of 'problems' is left unstated.

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?

Schema coverage is 83% — mode, angle, steps, persona and variantId all carry their own descriptions including enum semantics and examples. The prose only restates the mode split and the variant source, adding little beyond the schema. The undocumented required 'id' parameter is not clarified either, so the description does not compensate where it could.

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 states a specific verb and resource: 'Write emails with AI from the offer profile', 'Drafts a whole sequence (mode sequence) or a new version of one variant'. It distinguishes the two operating modes, but does not contrast itself against the sibling set_sequence, which sounds adjacent enough that an agent might hesitate between them.

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?

The modes are tied to conditions ('sequence = draft a whole sequence', 'rewrite, shorter, angle = a new version of one variant') and a prerequisite is spelled out: the workspace's offer profile must be configured in Ballast settings, otherwise use update_offer_profile. No explicit exclusions or sibling alternatives are named, which keeps it short of a 5.

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

All Ballast - Cold Email 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?