Skip to main content
Glama

Social Fetch

by io.github.social-freak-ltd
OverviewDiscussionsAdmin

Search TikTok Ad Library ads

tiktok_adLibrary_ads_search_get
Read-only

Search the public TikTok Ads Library by keyword or advertiser name. Returns a list (use cursor when paginated).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoAlias for `query`. Prefer `query`.
trimNoIgnored if this tool does not support it.
limitNoIgnored if this tool does not support it.
queryNoKeyword to search the public TikTok Ads Library.
cursorNoOpaque pagination cursor from a previous response.
offsetNoIgnored if this tool does not support it.
contextYesDescribe the user's underlying goal in one sentence — not the tool you are calling.
keywordsNoAlias for `query`. Prefer `query`.
pageSizeNoIgnored if this tool does not support it.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
maxResultsNoIgnored if this tool does not support it.
max_resultsNoIgnored if this tool does not support it.
advertiserNameNoSearch the public TikTok Ads Library by advertiser name.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / keywords
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `query`. Prefer `query`."
+}
    • addedInput schema / properties / limit
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}
    • addedInput schema / properties / maxResults
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}
    • addedInput schema / properties / max_results
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}
    • addedInput schema / properties / pageSize
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}
    • addedInput schema / properties / q
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `query`. Prefer `query`."
+}
    • addedInput schema / properties / trim
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}
  2. Changed11 schema fields changed
    • removedInput schema / properties / adFormat
      Removed value: -{
-  "description": "Ad format filter for Top Ads. `spark-ads`: ads boosted from an organic creator/brand TikTok post. `non-spark-ads`: ads uploaded directly as ad creative, not boosted from an existing post.",
-  "enum": [
-    "spark-ads",
-    "non-spark-ads"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / adLanguage
      Removed value: -{
-  "description": "Ad language filter for Top Ads.",
-  "enum": [
-    "en",
-    "es",
-    "ar",
-    "vi",
-    "th",
-    "de",
-    "id",
-    "pt",
-    "fr",
-    "ms",
-    "nl",
-    "ja",
-    "it",
-    "ro",
-    "zh-Hant",
-    "ko"
-  ],
-  "type": "string"
-}
    • changedInput schema / properties / advertiserName / description
      Previous value: -"Search the public TikTok Ads Library by advertiser name. When set, results come from the public Ads Library instead of Top Ads."New value: +"Search the public TikTok Ads Library by advertiser name."
    • removedInput schema / properties / duration
      Removed value: -{
-  "description": "Video duration filter for Top Ads.",
-  "enum": [
-    "under-10s",
-    "10-20s",
-    "20-30s",
-    "30-40s",
-    "40-50s",
-    "over-50s"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / industry
      Removed value: -{
-  "description": "Industry filter for Top Ads.",
-  "enum": [
-    "apparel-accessories",
-    "appliances",
-    "apps",
-    "baby-kids-maternity",
-    "beauty-personal-care",
-    "business-services",
-    "ecommerce-non-app",
-    "education",
-    "financial-services",
-    "food-beverage",
-    "games",
-    "health",
-    "home-improvement",
-    "household-products",
-    "life-services",
-    "news-entertainment",
-    "pets",
-    "sports-outdoor",
-    "tech-electronics",
-    "travel",
-    "vehicle-transportation"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / likes
      Removed value: -{
-  "description": "Likes percentile filter for Top Ads.",
-  "enum": [
-    "top-1-20",
-    "top-21-40",
-    "top-41-60",
-    "top-61-80",
-    "top-81-100"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / objective
      Removed value: -{
-  "description": "Campaign objective filter for Top Ads.",
-  "enum": [
-    "app-installs",
-    "conversions",
-    "lead-generation",
-    "product-sales",
-    "reach",
-    "traffic",
-    "video-views"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / orderBy
      Removed value: -{
-  "description": "Sort metric for Top Ads. `cvr`: conversion rate. `ctr`: click-through rate. `play-2s-rate`/`play-6s-rate`: rate viewers played past the 2s/6s mark. Default: `for-you`.",
-  "enum": [
-    "for-you",
-    "impression",
-    "play-2s-rate",
-    "play-6s-rate",
-    "cvr",
-    "ctr",
-    "like"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / period
      Removed value: -{
-  "description": "Time window in days for Top Ads.",
-  "enum": [
-    "7",
-    "30",
-    "180"
-  ],
-  "type": "string"
-}
    • changedInput schema / properties / query / description
      Previous value: -"Optional keyword to search ad titles and content."New value: +"Keyword to search the public TikTok Ads Library."
    • removedInput schema / properties / region
      Removed value: -{
-  "description": "Country code for Top Ads results. Default: `US`.",
-  "enum": [
-    "DZ",
-    "AR",
-    "AU",
-    "AT",
-    "AZ",
-    "BH",
-    "BD",
-    "BY",
-    "BE",
-    "BO",
-    "BR",
-    "BG",
-    "KH",
-    "CA",
-    "CL",
-    "CO",
-    "CR",
-    "HR",
-    "CY",
-    "CZ",
-    "DK",
-    "DO",
-    "EC",
-    "EG",
-    "EE",
-    "FI",
-    "FR",
-    "DE",
-    "GR",
-    "GT",
-    "JO",
-    "HU",
-    "ID",
-    "IQ",
-    "IE",
-    "IL",
-    "IT",
-    "JP",
-    "KZ",
-    "KE",
-    "KW",
-    "LV",
-    "LB",
-    "MY",
-    "MX",
-    "MA",
-    "NL",
-    "NZ",
-    "NG",
-    "NO",
-    "OM",
-    "PK",
-    "PA",
-    "PY",
-    "PE",
-    "PH",
-    "PL",
-    "PT",
-    "PR",
-    "QA",
-    "LT",
-    "RO",
-    "SA",
-    "RS",
-    "SG",
-    "SK",
-    "SI",
-    "ZA",
-    "KR",
-    "ES",
-    "LK",
-    "SE",
-    "CH",
-    "TW",
-    "TH",
-    "TR",
-    "AE",
-    "GB",
-    "US",
-    "UY",
-    "VN"
-  ],
-  "type": "string"
-}
  3. Changed5 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Describe the user's underlying goal in one sentence — not the tool you are calling.",
+  "type": "string"
+}
    • addedInput schema / properties / conversation_id
      Added value: +{
+  "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.",
+  "type": "string"
+}
    • addedInput schema / properties / llm_model
      Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}
    • addedInput schema / required
      Added value: +[
+  "context",
+  "llm_model"
+]
  4. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  5. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / adFormat / description
      Previous value: -"Ad format filter for Top Ads."New value: +"Ad format filter for Top Ads. `spark-ads`: ads boosted from an organic creator/brand TikTok post. `non-spark-ads`: ads uploaded directly as ad creative, not boosted from an existing post."
    • changedInput schema / properties / orderBy / description
      Previous value: -"Sort metric for Top Ads. Default: `for-you`."New value: +"Sort metric for Top Ads. `cvr`: conversion rate. `ctr`: click-through rate. `play-2s-rate`/`play-6s-rate`: rate viewers played past the 2s/6s mark. Default: `for-you`."
  6. Changed2 schema fields changed
    • changedInput schema / properties / orderBy / description
      Previous value: -"Sort metric for Top Ads. Defaults to for-you when omitted."New value: +"Sort metric for Top Ads. Default: `for-you`."
    • changedInput schema / properties / region / description
      Previous value: -"Country code for Top Ads results. Defaults to US when omitted."New value: +"Country code for Top Ads results. Default: `US`."
  7. First observed

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, and the description is consistent with them — searching a public library is inherently read-only, so there is no contradiction. The description adds value beyond annotations by disclosing the return type ('Returns a list') and the pagination mechanism ('use cursor when paginated'), which the agent would otherwise have to infer. It omits potential rate limits and data freshness, but the annotations carry the safety burden.

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?

Two sentences with no filler: the first states what is searched and by what means, the second states the return type and pagination rule. The purpose is front-loaded and every word earns its place.

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

Completeness4/5

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

For a read-only search tool, the description is mostly sufficient: the schema fully documents all 14 parameters, the required context and llm_model fields are explained there, and annotations cover the safety profile. The main gaps are that there is no output schema and the description only says 'list' without hinting at item shape, and no guidance distinguishes it from tiktok_adLibrary_ad_get; these are minor for a simple search tool.

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% — every parameter, including aliases q/keywords and the generic 'Ignored if this tool does not support it' fields, is documented in the schema. The description reinforces the two meaningful query modes and the cursor parameter at a high level but does not add factual content beyond what the schema already states, so the baseline of 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?

The description states a specific verb and resource — 'Search the public TikTok Ads Library' — along with the two search dimensions, 'by keyword or advertiser name,' which map to the query and advertiserName parameters. The 'public TikTok Ads Library' phrasing and the TikTok prefix in the name visually distinguish it from facebook_adLibrary_ads_search_get and google_adLibrary_advertisers_search, though it never explicitly names a sibling it is not.

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 description implies when to call the tool: when you need ads from the public TikTok Ads Library by keyword or advertiser name. 'Use cursor when paginated' is a concrete invocation hint. However, it gives no exclusions and no pointers to alternatives such as tiktok_adLibrary_ad_get for fetching a single ad, nor does it note that other platforms (Facebook, Google, LinkedIn) have separate ad-library search tools.

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

All Social Fetch toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources