Facebook Ad Library MCP

What changed for an advertiser

diff_advertiser

Read-onlyIdempotent

Compare an advertiser's Facebook ads against the last server snapshot, showing which ads started or stopped running. First call records a baseline; later calls show changes.

Instructions

Compare an advertiser's ads now against the last time this server looked, and report what they started and stopped running. The first call on a Page records a baseline and reports nothing changed, which is expected: call it again later to see movement. This is the only tool here that answers 'what changed' rather than 'what is running'.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	How many ads to pull for the comparison. Keep it consistent between calls.
`country`	No	Two-letter country code. Default US.
`page_id`	Yes	Advertiser Page ID to compare. Get it from list_advertisers.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`note`	Yes
`page_id`	Yes
`running_now`	No
`tracked_now`	No
`no_longer_seen`	No
`started_running`	No
`baseline_created`	Yes
`previously_tracked`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.6.1Oct 6, 2026
- removedInput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
- removedInput schema / additionalProperties
```
Removed value: -false
```
- removedOutput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
First observedv0.4.0Sep 1, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, open-world behavior, so the description's added value is the baseline/no-op-on-first-call semantics and the dependency on when the server last looked, both genuinely non-obvious. It stops short of anything about snapshot freshness limits, rate limits, or how a large limit affects the diff, so it is strong but not exhaustive.

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 sentences, front-loaded with the action and outcome, then the baseline caveat, then the sibling differentiation. No filler and nothing buried.

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?

An output schema exists, so return shape need not be explained; the description instead spends its words on the one thing an agent would otherwise get wrong (the empty first diff). For a 3-parameter read tool with full annotation coverage, nothing needed to call it correctly is missing.

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 page_id, limit and country, including the 'keep limit consistent between calls' advice. The description adds no parameter-level detail beyond the comparison framing, which is the expected baseline when the schema does the heavy lifting.

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: compare an advertiser's ads against the last snapshot and report what started/stopped. It explicitly positions itself against every sibling with 'the only tool here that answers "what changed" rather than "what is running"', so an agent can route without opening another schema.

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

Usage Guidelines5/5

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

Gives the non-obvious usage condition directly: the first call records a baseline and reports no change, so it must be called again later to observe movement. It also states the differentiation from search_ads/list_advertisers-style tools, leaving little to inference.

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

Deploy Server