Skip to main content
Glama

Update a step

update_campaign_step
DestructiveIdempotent

Use this when the user wants to change one step: a manual step's subject and body (sent together, they replace its whole message), an AI step's topic, the days it waits, or an A/B split's weights. A condition takes only its waiting window. It answers the step's id only. Free.

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": {
      "campaignId": "<campaignId>",
      "stepId": "<stepId>"
    },
    "name": "update_campaign_step"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoA `manual` step's new message, sent with `subject`. On a `linkedin_connection` step, the invitation note, up to 200 characters.
topicNoWhat an AI step should say. Its title is written again from it.
stepIdYesThe step's id, as the campaign's steps list gives it.
subjectNoA `manual` step's new subject line, sent with `body`: the two replace the step's whole message.
splitArmsNoAn A/B split's variants, its only field: both, `a` then `b`, with weights adding up to 100. Leads not yet written to follow the new weights.
campaignIdYesThe campaign's id.
daysBetweenNoDays to wait after the step before, 0 to 365. On a condition, its window, 1 to 30, and the only field it takes.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds real context on top: subject and body 'replace its whole message' (the destructive scope), split weights only affect leads not yet written, a condition accepts only its window, and the response is the step id only. It also notes the call is 'Free', a quota fact no annotation carries.

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 short sentences, front-loaded with the trigger, then the field-by-type rules, then the return and cost. No filler; even the terse 'Free.' carries information.

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 compensates by stating the return value ('answers the step's id only'), and it covers every step type the tool mutates. It leaves out error behavior and whether a preview is advisable before a destructive message replacement, which would round it out.

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 cross-parameter semantics the schema states only piecemeal: subject and body must be sent together as a pair, and a condition takes daysBetween as its only field. It does not add format or validation detail beyond the schema.

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?

States a specific verb and resource ('change one step') and then enumerates exactly which fields apply to which step type: manual subject/body, AI topic, wait days, A/B weights, condition window. An agent can tell this apart from add/delete/copy step siblings without opening any schema.

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?

'Use this when the user wants to change one step' gives a clear trigger condition, and the per-step-type field mapping tells the agent which edits are legal. It stops short of naming alternatives (e.g. preview_campaign_step before applying, copy_campaign_step_variant for variants), so there is no explicit 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.

Resources