EmailFig

Update campaign draft

update_campaign_draft

DestructiveIdempotent

Changes a draft this chat app created, until someone saves it in EmailFig. Only the fields given change, and they mean what they mean in create_campaign_draft. It never sends.

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": "update_campaign_draft"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	The draft's id from create_campaign_draft.
`body`	No	Exactly one of: blocks (the editor format from get_email_format), html, or template_id. Use blocks unless the person gave you HTML or chose a template.
`name`	No	What the campaign is called in EmailFig.
`subject`	No
`audience`	No	Who it goes to, one of: { everyone: true }, { list_ids: [...] }, or { tag_ids: [...], segment_ids: [...] }.
`preview_text`	No	The line inboxes show after the subject.
`subscription_list_id`	No	A list list_lists marks as a subscription_list: people can subscribe to it and leave, and anyone who left is skipped. Needed before sending when the account has such lists. Null clears it.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Adds meaningful behavior beyond the annotations: partial-update semantics ("Only the fields given change"), the draft-only lifecycle constraint, and the guarantee that no send occurs. It does not explain the destructiveHint=true implication (what gets overwritten/lost) or what happens if the draft is no longer a draft, leaving that risk undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three very short sentences with the scope constraint front-loaded and zero filler. Each sentence carries a distinct fact: partial update, field semantics source, and no-send guarantee.

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 7-parameter nested mutation with rich schema descriptions and full annotation coverage, the description supplies the critical extras: partial-update behavior, draft lifecycle, and no-send. Missing are error behavior when the draft is already saved and any note on the destructive-overwrite risk, but these are secondary given the schema richness.

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 86%, so the schema already carries most parameter meaning, and the description's main contribution is deferring field semantics to create_campaign_draft — useful but indirect, forcing the agent to consult another tool. No additional syntax or format details are offered for the 7 nested 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?

States a specific verb+resource ("Changes a draft") and narrows scope to drafts "this chat app created," which distinguishes it from create_campaign_draft. The phrase "until someone saves it in EmailFig" hints at an expiry condition but is oblique enough that an agent may not immediately grasp that the tool only works on unsaved drafts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage context (modify a chat-app-created draft) and gives one boundary condition ("It never sends"), but never states when not to use it — e.g., what to do for an already-saved campaign, or which sibling to call instead. Guidance is inferred rather than explicit.

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

All EmailFig 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.