Skip to main content
Glama

ADS Beast

update_campaign_draft

Replace fields of a draft that was created with create_campaign_draft and has not been published: each field passed replaces the stored one whole (ad_groups replaces all ad groups). Returns the draft with a fresh validation. Drafts made by a person in the builder and builds that were already published are refused. Nothing is sent to the ad platform.

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": {
      "draft_id": "<draft_id>"
    },
    "name": "update_campaign_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
geoNoCountry codes ('UA', 'SK'); Google also takes 'City, CC'. Meta takes country codes only.
nameNo
extraNopage_id, instagram_actor_id, dsa_beneficiary, dsa_payor, structured_snippets, search_partners, display_network, geo_target_type, vertical, devices, job_titles, industries, cities, regions.
notesNoA note for the person who will review the draft: what it is for and what to check.
audienceNoSocial types: age_min, age_max, genders, interests, placements, custom_audiences, allow_broad_audience + broad_audience_reason.
draft_idYesDraft id returned by create_campaign_draft.
ad_groupsNoAd groups (ad sets) with their keywords and ads. The exact fields and limits per type are in list_campaign_types.
languagesNoLanguage codes of the audience ('uk', 'en').
conversionNoMeta leads/sales: {type: 'website', pixel_id, event} or {type: 'lead_form', lead_form_id}.
target_cpaNoTarget cost per result in the account currency, when the strategy needs one.
landing_urlNohttps landing page used for every ad that has no final_url of its own.
target_roasNo
bid_strategyNoSee default_bid_strategies of the type in list_campaign_types; empty keeps the platform default.
daily_budgetNoPer day, in the currency of the client's ad account.
negative_keywordsNoCampaign-level negative keywords (search types).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is partly covered. The description still adds real value by disclosing whole-field replacement semantics ('ad_groups replaces all ad groups'), the fresh-validation return, and that nothing is sent to the ad platform. It does not say whether omitted fields are preserved or cleared, which matters for a replace-style mutation.

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?

Four short sentences, front-loaded with the core action and scope, then replacement semantics, then return value, then refusals. No filler and no repetition of schema content.

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 15-parameter nested mutation with no output schema, the description covers the essentials: eligibility, replacement semantics, return shape and side-effect boundary. It leaves the validation-failure behavior and the preserve-vs-clear question for omitted fields unstated.

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 87%, so the schema already documents most parameters and the baseline is 3. The description adds meaning the schema cannot: that each passed field replaces the stored value wholesale, with ad_groups as the concrete example, which changes how an agent should construct the call.

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 and resource ('Replace fields of a draft') plus the exact scope: drafts created via create_campaign_draft that are unpublished. It clearly separates itself from the create path and from published builds, though it does not distinguish itself from the similarly named campaign_draft_edit sibling.

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?

Gives explicit preconditions (must be a draft created by create_campaign_draft, must not be published) and explicit exclusions (person-made builder drafts and already-published builds are refused). It stops short of naming an alternative tool for those refused cases, so the agent must infer where to go next.

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.