Skip to main content
Glama

Proxy

by dev.useproxy
OverviewDiscussionsAdmin

Analyze Ad Video Content

analyze_ad_video
Read-only

Use this when you want to analyze video ad content or get a transcript of a video ad - the response includes a timestamped Full Transcript section (verbatim voiceover/dialogue; quote it directly when the user asks for a transcript), plus visual storytelling, audio elements, pacing, scene transitions, and brand messaging using AI video understanding. PREFER passing ad_archive_id + page_id (Meta) or tiktok_id over media_url — signed CDN URLs (fbcdn, tiktokcdn, byteoversea) expire within minutes; the server fetches a fresh URL when you pass stable IDs. Param precedence: tiktok_id > ad_archive_id + page_id > media_url (mutually exclusive branches). Follow up with get_competitive_brief to synthesize patterns across analyzed ads.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ad_idNoAd ID echoed in the response. URL resolution uses ad_archive_id or tiktok_id.
contextNoOne plain sentence, 8-20 words, starting with a verb, stating what the user is trying to accomplish in this conversation. Name the brand, competitor, industry, or topic involved. Reuse the exact same sentence on every tool call in this conversation. Never include people's names, emails, phone numbers, credentials, or internal company details. Never describe this tool or why it was chosen. Example: 'Compare Notion and Coda Meta ads to find hooks for a productivity app launch.'
page_idNoMeta Platform ID of the page that ran the ad. Required with ad_archive_id.
media_urlNoDirect video URL. Signed CDN URLs expire within minutes, so use only a freshly returned one; stable IDs are more reliable.
tiktok_idNoTikTok ad ID from search_tiktok_ads or get_tiktok_ad_details. The server fetches a fresh video URL (1 credit).
brand_nameNoBrand name, for context.
ad_archive_idNoMeta ad_id from get_meta_ads. With page_id, the server fetches a fresh video URL.
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.
total_impressionsNoImpression count or range string (e.g. 1500000 or "700K - 800K") from get_meta_ads; enables performance-weighted analysis.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
_mcp_instructionsNoServer-issued metadata for this conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / ad_archive_id / description
      Added value: +"Meta ad_id from get_meta_ads. With page_id, the server fetches a fresh video URL."
    • addedInput schema / properties / ad_id / description
      Added value: +"Ad ID echoed in the response. URL resolution uses ad_archive_id or tiktok_id."
    • addedInput schema / properties / brand_name / description
      Added value: +"Brand name, for context."
    • addedInput schema / properties / media_url / description
      Added value: +"Direct video URL. Signed CDN URLs expire within minutes, so use only a freshly returned one; stable IDs are more reliable."
    • addedInput schema / properties / page_id / description
      Added value: +"Meta Platform ID of the page that ran the ad. Required with ad_archive_id."
    • addedInput schema / properties / tiktok_id / description
      Added value: +"TikTok ad ID from search_tiktok_ads or get_tiktok_ad_details. The server fetches a fresh video URL (1 credit)."
    • addedInput schema / properties / total_impressions / description
      Added value: +"Impression count or range string (e.g. 1500000 or \"700K - 800K\") from get_meta_ads; enables performance-weighted analysis."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, non-destructive), so the bar is lower; the description still exceeds it by disclosing that signed CDN URLs (fbcdn/tiktokcdn/byteoversea) expire within minutes, that the server re-fetches a fresh URL for stable IDs, and that tiktok_id costs 1 credit. These are non-obvious operational behaviors an agent must know to call correctly.

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?

Front-loaded with the use case and dense with actionable content, so every clause earns its place. It is a single long paragraph heavy with em-dashes and parentheticals, which makes it slightly harder to scan than it could be.

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 values needn't be re-explained, yet the description still summarizes the response shape (transcript plus analytic sections) and links the next step. For a 9-parameter, zero-required tool, nothing an agent needs to select or invoke it is missing.

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 baseline is 3; the description adds genuine meaning on top by defining the resolution precedence ('tiktok_id > ad_archive_id + page_id > media_url') and the coupling rule that page_id is required with ad_archive_id, which the per-parameter schema text does not state as a whole.

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+resource ('analyze video ad content') and enumerates the concrete outputs (timestamped Full Transcript, visual storytelling, audio elements, pacing, scene transitions, brand messaging). 'Video' distinguishes it cleanly from the sibling analyze_ad_image.

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?

Explicitly gives the triggering condition ('Use this when you want to analyze video ad content or get a transcript'), recommends the stable-ID path over media_url, states the mutual-exclusivity precedence chain, and names the follow-up sibling get_competitive_brief. Nothing is left to inference.

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

All Proxy 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