Skip to main content
Glama
Ads MCP for Snapchat

Ads MCP for Snapchat

by Usame794

snap_health_check

Read-only

Audit active campaigns and ad squads to flag missing buyer exclusion, high frequency, low swipe rate or ROAS, spend without purchases, and squads under paused campaigns; return ad squad IDs to act on.

Instructions

Audit every ACTIVE campaign's ACTIVE ad squads (read-only): no buyer exclusion, high frequency, low swipe rate, low ROAS, spend with no purchases, squads under a paused campaign. Returns the ad squad ids to act on.

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": {
      "start_time": "<start_time>",
      "end_time": "<end_time>"
    },
    "name": "snap_health_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
end_timeYes
min_roasNo
min_spendNo
start_timeYesWindow start, e.g. 2026-10-19T00:00:00+00:00
max_frequencyNo
min_swipe_rate_pctNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the explicit 'read-only' label is partly redundant. What the description does add is substantive: the complete list of flagging conditions and the fact that the response is a set of ad squad ids intended for follow-up action, which tells the agent this is a diagnostic entry point rather than a mutator.

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?

A single dense sentence with the scope and the return value front-loaded; almost no waste. The condition list is long but each item is a distinct check that earns its place.

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

Completeness3/5

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

For a six-parameter, low-coverage, no-output-schema tool, the description covers purpose and return shape but omits the time window semantics (start_time/end_time format is only in the schema), the meaning and defaults of the four threshold parameters, and any note on result volume or ordering. Adequate to select the tool, thin for invoking it precisely.

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 only 17% (only start_time is documented), so the description must compensate. It partly does: the enumerated conditions map onto the threshold parameters (high frequency → max_frequency, low swipe rate → min_swipe_rate_pct, low ROAS → min_roas, spend with no purchases → min_spend), giving the agent semantic grounding. However, it never names these parameters, states their defaults, or clarifies directionality, so an agent still has to read the schema to bind values.

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 ('Audit every ACTIVE campaign's ACTIVE ad squads') and enumerates the exact conditions checked: no buyer exclusion, high frequency, low swipe rate, low ROAS, spend with no purchases, squads under a paused campaign. It also states the output ('Returns the ad squad ids to act on'), which distinguishes it from sibling health checks like snap_audience_health or snap_pixel_health that operate on different entities.

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

Usage Guidelines3/5

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

The 'ACTIVE campaign / ACTIVE ad squads' scoping and 'ids to act on' framing imply this is a pre-optimization audit pass, but there is no explicit when-to-use or when-not guidance and no named alternative (e.g., when to prefer snap_anomaly_check or snap_audience_health). Usage must be inferred.

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

Deploy Server

Other Tools