Skip to main content
Glama

Captapi

by io.github.CDCStream
OverviewDiscussionsAdmin

youtube_summarize

AI summary from YouTube's published captions — same source as /transcript. Flat 3 credits; caption-miss 404 is free. Costs 3 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).

Input Schema

NameRequiredDescriptionDefault
urlYesPublic YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook, LinkedIn to X/Twitter, or Pinterest to Rumble.
cacheNoSet true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh.
languageNoPreferred caption language as an ISO code, e.g. "en". Defaults to auto-detect.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / cache / description
      Previous value: -"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. Envelope includes cached + cachedAt on hits."New value: +"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh."
  2. Changed2 schema fields changed
    • changedInput schema / properties / cache / description
      Previous value: -"Set true to serve from the 24h response cache. Default false — always fetch fresh data."New value: +"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. Envelope includes cached + cachedAt on hits."
    • changedInput schema / properties / url / description
      Previous value: -"Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this tool's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook, LinkedIn to X/Twitter, or Pinterest to Rumble."New value: +"Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook, LinkedIn to X/Twitter, or Pinterest to Rumble."
  3. Changed1 schema field changed
    • changedInput schema / properties / cache / description
      Previous value: -"Responses are cached for 24 hours by default. Set false to bypass the cache and always fetch fresh data (default true)."New value: +"Set true to serve from the 24h response cache. Default false — always fetch fresh data."
  4. Changed1 schema field changed
    • addedInput schema / properties / cache
      Added value: +{
+  "description": "Responses are cached for 24 hours by default. Set false to bypass the cache and always fetch fresh data (default true).",
+  "type": "boolean"
+}
  5. Changed1 schema field changed
    • changedInput schema / properties / url / description
      Previous value: -"Public YouTube video URL, e.g. https://youtube.com/watch?v=ID."New value: +"Public YouTube video URL, e.g. https://youtube.com/watch?v=ID. Not a TikTok/Instagram/Facebook URL. The URL platform must match this tool's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook, LinkedIn to X/Twitter, or Pinterest to Rumble."
  6. First observed

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a good job on the operational side: flat 3-credit cost, free caption-miss 404, no charge for empty results or failures, and cache-hit behavior. What is missing is output behavior—it never says what the summary output looks like (length, format, language of output), which matters for a summarization tool. Still, the billing/caching/error transparency is substantial.

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

Conciseness3/5

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

The description is short and front-loaded, but it is redundant: 'Flat 3 credits' and 'Costs 3 credits' state the same fact twice, and the cache point partially repeats the schema. Sentences earn their place individually but the repetition costs it a point.

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?

There is no output schema and no annotations, so the description should ideally explain the return value. It thoroughly covers cost, caching, and error charging, but omits any description of the summary output itself, which is the core of a summarization tool. Adequate but with a clear gap.

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%, so the schema already documents url, cache, and language. The description reinforces the cache parameter ('free 24h cache hit, default always fresh') but adds little beyond the schema, and says nothing extra about url or language. Baseline 3 is appropriate when the schema does the heavy lifting.

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: an 'AI summary from YouTube's published captions'. It also clarifies provenance by equating the source with '/transcript', which helps distinguish it from the youtube_transcript sibling. It does not, however, differentiate from video_summarize or youtube_shorts_summarize, leaving some sibling ambiguity.

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 guidance is implied rather than explicit: by saying the source is the 'same source as /transcript', an agent can infer that this is the summarized counterpart to youtube_transcript. There is no explicit when-to-use/when-not, no mention of the shorts/long-form distinction, and no alternative routing guidance. Most of the text is pricing rather than usage.

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

All Captapi 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