Skip to main content
Glama
Sign In

Nexscope

by io.github.nexscope
OverviewDiscussionsAdmin

Facebook Ad Library Ad Transcript

social_facebook_ad_library_ad_transcript
Read-only

Retrieves a transcript for a Facebook Ad Library video ad by ID or URL. Returned native captions cost 1 credit. Otherwise the public video URL is transcribed with AI. If the ad has no video or no transcript is available, transcript is null and the charge is 0 credits. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Completed lookups cost at least 10 Nexscope credits. Actual cost depends on the operation and requested options. Repeated requests may purchase data again. Facebook Ad Library Ad Transcript API View Pricing Get native captions or an AI transcript from a Facebook video ad. Long AI transcripts may time out. Native captions or AI up to 2 minutes: 1 credit. Paid AI mode: 10 credits/minute, rounded up, even for short videos. No transcript: 0 credits. Retrieves a transcript for a Facebook Ad Library video ad by ID or URL. Returned native captions cost 1 credit. Otherwise the public video URL is transcribed with AI. If the ad has no video or no transcript is available, transcript is null and the charge is 0 credits. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Paid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. If we have a response in the cache that is this many days old or newer, return the cached response (0 credits, with "cached": true and a "cached_at" timestamp). Otherwise, scrape a live result (Returned native captions cost 1 credit, even for long videos with the paid flag. By default, successful AI up to 120 seconds costs a flat 1 credit per request; over 120 seconds requires allow_long_transcription=true, which bills ALL successful AI at 10 credits per started minute, including short videos; empty AI results and errors cost 0 credits; no transcript: 0 credits). See the Caching page for details.

Input Schema

NameRequiredDescriptionDefault
idNoFacebook Ad Id
urlNoFacebook Ad URL
cache_max_ageNoIf we have a response in the cache that is this many days old or newer, return the cached response (0 credits, with "cached": true and a "cached_at" timestamp). Otherwise, scrape a live result (Returned native captions cost 1 credit, even for long videos with the paid flag. By default, successful AI up to 120 seconds costs a flat 1 credit per request; over 120 seconds requires allow_long_transcription=true, which bills ALL successful AI at 10 credits per started minute, including short videos; empty AI results and errors cost 0 credits; no transcript: 0 credits). [See the Caching page for details.](https://docs.scrapecreators.com/caching)
allow_long_transcriptionNoPaid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses the credit model in detail (1 credit native captions, 1 credit AI up to 120s, 10 credits per started minute in paid mode, 0 credits on null/error), synchronous behavior, a 30-second client timeout recommendation, caching semantics, and the possibility of timeout failure on long videos. That is genuinely rich behavioral context an agent needs before spending credits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is well front-loaded, but the body is severely bloated: the opening paragraph appears twice verbatim, and the allow_long_transcription and cache_max_age schema blurbs are pasted in whole as standalone paragraphs. The same pricing formula is repeated four or five times, so the agent must wade through redundancy to find anything new.

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 synchronous scraping tool with no output schema, the definition covers the important unknowns: cost per path, null-result behavior, timeout risk, and caching. Nothing critical is missing, though the absence of any explicit statement about what the transcript response contains or which of id/url is preferred leaves small gaps.

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%, and the enumerations and defaults are already documented in the schema. The description restates the allow_long_transcription and cache_max_age semantics almost verbatim rather than adding new meaning, so the baseline 3 applies. It does usefully clarify that the paid flag does not by itself force AI transcription, but that point is also present in the schema text.

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 opening sentence gives a specific verb and resource: 'Retrieves a transcript for a Facebook Ad Library video ad by ID or URL.' That is unambiguous and directly distinguishes it from the ad-detail sibling. However, it never explicitly routes the agent away from siblings like social_facebook_ad_library_ad or social_facebook_post_transcript, so differentiation is only implicit through the resource name.

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?

Usage context is implied through the cost/flag discussion: default is cheap AI for videos under 120s, and 'allow_long_transcription=true' is the escape hatch for longer videos. There is no explicit statement of when to call this tool versus fetching the ad itself, and no prerequisites or input-requirement guidance (e.g. supply id OR url).

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

All Nexscope 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