Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Check ad policy

check_ad_policy
Read-only

Check ad copy against Meta's live advertising standards before launch. Get a pass, fix, or block verdict with quoted policy text and a compliant rewrite.

Instructions

Pre-flight ad copy against Meta's REAL, live Advertising Standards before you run it — a flat 1-credit check. Pulls Meta's actual policy pages and returns a verdict (pass / fix / block) where every flagged issue QUOTES Meta's own policy text verbatim plus a compliant rewrite that keeps the sell. It's a check, not an edit — it never changes the creative. Especially worth running for regulated-adjacent categories (health/supplements, weight-loss or beauty results claims, finance/crypto/insurance, alcohol, dating, gambling) or ANY strong/absolute/guaranteed claim.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
copyYesthe ad copy / script / on-screen text to check
claimsNothe claims / proof points the ad makes
categoryNothe product category — helps pick the relevant policy pages
imageDescriptionNoa description of the creative / image when relevant

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.161
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "anchors": {
-      "description": "the Meta policy pages consulted ({url, …})",
-      "items": {},
-      "type": "array"
-    },
-    "findings": {
-      "description": "flagged issues ({severity, issue, policy_quote, fix_suggestion, where_in_ad})",
-      "items": {},
-      "type": "array"
-    },
-    "summary": {
-      "description": "one-line verdict summary",
-      "type": "string"
-    },
-    "verdict": {
-      "description": "pass / fix / block",
-      "type": "string"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already mark the tool as read-only and non-destructive, and the description adds rich behavioral detail beyond that: it is a 'flat 1-credit check,' it pulls Meta's actual live policy pages, every flagged issue quotes Meta verbatim, it provides a compliant rewrite, and it 'never changes the creative.' This is exactly the contextual behavior an agent needs to set expectations and avoid misuse.

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?

The description is compact and front-loaded: the first sentence states purpose, target, and cost; the second explains method and output; the third removes ambiguity about mutation; the fourth gives concrete use cases. Every sentence earns its place, and there is no repetition of schema or annotation content.

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?

Even though there is no output schema, the description fully compensates by specifying the verdict values ('pass / fix / block'), the quoting-and-rewrite behavior, the live policy source, the cost, and the target scenarios. Combined with 100% schema parameter descriptions and read-only annotations, an agent has everything needed to select and invoke this tool correctly.

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 description coverage is 100%, so the schema already documents all four parameters. The description adds meaningful semantic context on top: 'copy' is clarified as 'ad copy / script / on-screen text,' 'claims' maps to 'claims / proof points the ad makes,' and 'category' is explained as helping 'pick the relevant policy pages.' This goes beyond the baseline and connects the parameters to the tool's internal behavior.

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 opens with a specific verb and resource: 'Pre-flight ad copy against Meta's REAL, live Advertising Standards.' It also names the exact output form ('verdict (pass / fix / block)') and explicitly contrasts it with editing ('It's a check, not an edit'), which separates it clearly from sibling creative tools like plan_ad, render_ad, or post_to_meta.

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 gives explicit trigger conditions: run it before launching ads, especially for regulated-adjacent categories such as health, finance/crypto, alcohol, dating, gambling, or for any strong/absolute/guaranteed claim. It does not name alternative tools or state when not to use it, so it stops short of a full 5, but the when-to-use guidance is clear and actionable.

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