meta-ads-mcp

create_rf_prediction

Generate a reach and frequency prediction for a Meta ad campaign by providing targeting JSON, budget in cents, and scheduling details.

Instructions

Create a new reach & frequency prediction. Provide targeting spec as JSON string, budget in cents, and scheduling info.

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": {
      "target_spec": "<target_spec>",
      "start_time": "<start_time>",
      "stop_time": "<stop_time>",
      "budget": "<budget>",
      "frequency_cap": "<frequency_cap>",
      "destination_id": "<destination_id>"
    },
    "name": "create_rf_prediction"
  }
}

Input Schema

Name	Required	Description
`budget`	Yes	Budget in account currency cents
`stop_time`	Yes	Prediction stop time (ISO 8601 or Unix timestamp)
`account_id`	No	Ad account ID to create the prediction in (e.g. 'act_123' or '123'). Falls back to META_AD_ACCOUNT_ID env var if omitted.
`start_time`	Yes	Prediction start time (ISO 8601 or Unix timestamp)
`target_spec`	Yes	JSON string of targeting specification
`frequency_cap`	Yes	Maximum frequency cap per user
`destination_id`	Yes	Destination ID (e.g. Facebook Page ID)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.6.1Oct 21, 2026

addedInput schema / properties / account_id

Added value: +{
+  "description": "Ad account ID to create the prediction in (e.g. 'act_123' or '123'). Falls back to META_AD_ACCOUNT_ID env var if omitted.",
+  "type": "string"
+}

First observedv1.2.0Mar 19, 2026

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It says nothing about required permissions, whether the prediction runs asynchronously, what identifier is returned, or whether the prediction persists as a billable object. Only the parameter-adjacent hints (cents, JSON string) are offered.

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?

Two short sentences with zero filler and the core action front-loaded. It is efficient, though the second sentence is a loose enumeration that omits half the required parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a seven-parameter, six-required mutation tool with no annotations and no output schema, so the description should do more. It omits required inputs such as frequency_cap and destination_id, says nothing about the account_id fallback or the shape of the result, leaving an agent under-informed about what a successful call produces.

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 description coverage is 100%, so the schema already documents all seven parameters including the account_id env-var fallback and the ISO 8601 / Unix formats. The description repeats a subset (targeting spec as JSON string, budget in cents, scheduling info) but adds no syntax or constraints beyond the schema, so the baseline 3 applies.

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 ('Create') and resource ('reach & frequency prediction'), and the verb itself distinguishes it from the sibling read/delete tools list_rf_predictions, get_rf_prediction and delete_rf_prediction. It does not, however, explicitly differentiate itself from other creation or estimation siblings such as get_reach_estimate.

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

Usage Guidelines2/5

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

No when-to-use guidance is given. The description never explains when a reach & frequency prediction is the right choice versus get_reach_estimate, get_delivery_estimate, or creating an experiment, nor does it state prerequisites.

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

Deploy Server