Skip to main content
Glama
DatalisHQ

ZuckerBot

by DatalisHQ

zuckerbot_create_campaign_from_spec

Construct a Meta campaign from a declarative JSON spec. Validate with dry_run to inspect resolved payloads, then build paused campaigns.

Instructions

Build a complete Meta campaign VERBATIM from a declarative JSON spec — no strategy generation, no copy authoring. Everything is created PAUSED, always; launching remains a separate deliberate call. Recommended flow: send with dry_run=true first to get the fully resolved Graph API payloads without creating anything, review them, then re-send without dry_run to build. Validation failures return an errors array of per-field {path, message, kind: schema|semantic} entries — fix each path and retry. Spec shape: campaign {name, objective OUTCOME_LEADS|OUTCOME_SALES, budget {type CBO_DAILY, amount, bid_strategy HIGHEST_VOLUME|LOWEST_COST_WITHOUT_CAP|COST_CAP}, special_ad_categories}, ad_sets [{name, conversion_location WEBSITE|INSTANT_FORM, attribution {click_days 1|7, view_days 0|1}, targeting {geo — ARRAY of 2-letter country codes e.g. ["AU"], age_min, advantage_audience, excluded_custom_audiences}, placements {mode MANUAL|ADVANTAGE_PLUS, exclude}; WEBSITE additionally: pixel_id, optimisation_event {type CUSTOM_CONVERSION, id}|{type STANDARD, event e.g. Lead}, performance_goal MAXIMISE_CONVERSIONS (the Ads Manager label, not the Graph enum); INSTANT_FORM instead: lead_form_id — the Meta instant form on the connected Page (no pixel_id, no optimisation_event, and its ads take NO final_url — the form is the destination; single-image creative, no multi-ratio placement customisation)}], ads [{name, asset {type IMAGE_SET, refs {1x1,4x5,9x16 — https URLs or uploaded image hashes}}|{type VIDEO, ref — pre-uploaded Meta video id}|{type EXISTING_AD, ad_id — clones that ad's image/video asset from the SAME ad account; copy, CTA and destination come from THIS spec}, primary_text, headline, description, cta, final_url (WEBSITE ad sets only), ad_set_name?}]. EXISTING_AD specs need Meta credentials even for dry_run (the source asset is read from Meta). Use zuckerbot_list_custom_conversions to find custom conversion ids.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
specYesThe declarative campaign spec (see tool description for the shape)
dry_runNotrue = return the resolved Graph payloads without creating anything. Strongly recommended before a real build
business_idNoOptional business ID override for the authenticated API key
Behavior4/5

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

With no annotations provided, the description covers key behaviors: campaigns are always created paused, dry_run behavior, validation error format, and special requirements (e.g., EXISTING_AD needs credentials even for dry_run). It could mention implications of resending with changes, but overall is quite comprehensive.

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?

The description is lengthy but well-structured: first sentence on purpose, then paused behavior, recommended flow, validation, and a detailed breakdown of the spec shape. It uses clear formatting with brackets and parentheses. Minor redundancy (e.g., 'always' emphasized twice), but overall efficient.

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?

Given the tool's complexity (nested objects, multiple ad types, conditional fields, no output schema), the description is exceptionally thorough. It covers error handling, dry run, special cases, and references a sibling tool for conversions. The agent can confidently construct and call this tool based solely on the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds extensive detail about the nested spec object, including all fields, enums, conditional requirements (e.g., WEBSITE vs INSTANT_FORM), and asset types. This far exceeds what the minimal schema provides, giving the agent full parameter semantics.

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 description starts with 'Build a complete Meta campaign VERBATIM from a declarative JSON spec', clearly stating the tool's purpose. It explicitly says it does not generate strategy or copy, distinguishing it from siblings like zuckerbot_create_full_campaign and zuckerbot_generate_campaign_brief.

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 description provides a recommended flow: use dry_run first, review payloads, then re-send without dry_run. It also mentions using zuckerbot_list_custom_conversions for finding conversion IDs. However, it does not explicitly state when not to use this tool versus alternatives, though the spec-driven nature implies it is for users with a complete spec.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DatalisHQ/zuckerbot'

If you have feedback or need assistance with the MCP directory API, please join our Discord server