SavedThat

Get a focused transcript moment

get_moment

Read-onlyIdempotent

Fetch a focused window (about 2 minutes by default) around one moment in a video the user saved, which gives enough context to act on the idea without returning a whole long video. Takes the url and timestamp of a candidate returned by search_my_library. Short videos come back in full. The result carries a source: transcript means spoken words, which can be quoted, while visual means the video has no speech at all and the window is the indexer's own scene and on-screen-text descriptions, which read honestly only as a description of what is on screen. When found is false, read reason before answering: not_processed_yet means SavedThat is still transcribing that video, so say it is on its way and can be asked for again shortly rather than reporting nothing found; not_in_library means the user never saved it; transcription_failed means SavedThat tried and could not; no_window_match means the timestamp is past the end of a video duration_seconds long.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>",
      "at": "<at>"
    },
    "name": "get_moment"
  }
}

Input Schema

Name	Required	Description
`at`	Yes	Timestamp of the moment: seconds, or mm:ss / h:mm:ss.
`url`	Yes	The saved video URL (from a search candidate).
`window_sec`	No	Half-window in seconds (total context is about twice this).

Output Schema

Name	Required	Description
`at`	No
`url`	No
`full`	No
`found`	Yes
`range`	No
`title`	No
`reason`	No	Present only when found is false: WHY. not_processed_yet means SavedThat is still transcribing that video, so the transcript is on its way; transcription_failed means SavedThat tried and could not, so nothing is on its way and the user should not be told to wait; not_in_library means the user never saved it, which also covers a video SavedThat has never seen; no_window_match means the timestamp lies past the end of the video.
`source`	No
`channel`	No
`platform`	No
`deep_link`	No
`at_seconds`	No
`transcript`	No
`thumbnail_url`	No
`duration_seconds`	No	With reason no_window_match: how long that video actually is.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 10, 2026

addedOutput schema / properties / duration_seconds

Added value: +{
+  "description": "With reason no_window_match: how long that video actually is.",
+  "type": "integer"
+}

addedOutput schema / properties / reason

Added value: +{
+  "description": "Present only when found is false: WHY. not_processed_yet means SavedThat is still transcribing that video, so the transcript is on its way; transcription_failed means SavedThat tried and could not, so nothing is on its way and the user should not be told to wait; not_in_library means the user never saved it, which also covers a video SavedThat has never seen; no_window_match means the timestamp lies past the end of the video.",
+  "enum": [
+    "missing_url",
+    "invalid_at",
+    "unsupported_url",
+    "no_video_id",
+    "not_processed_yet",
+    "transcription_failed",
+    "not_in_library",
+    "no_transcript",
+    "no_window_match"
+  ],
+  "type": "string"
+}

First observedNov 9, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses the default window size, that short videos come back in full, and the meaning of the `source` field (transcript vs visual scene descriptions) with a caveat about how visual output may be quoted. It also gives per-value handling for `found: false` — a genuinely useful behavioral contract.

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?

Purpose is front-loaded and the enumerated failure reasons each carry actionable handling guidance rather than filler. The single dense paragraph is long and could be split or tightened, but almost every clause earns its place.

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, yet the description still explains the semantics of `source`, `found`, and `reason`, which are exactly the fields an agent must interpret to answer the user correctly. Nothing material for correct invocation or interpretation 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 coverage is 100%, so the baseline is 3; the description adds real meaning by anchoring `url` and `at` to a prior search candidate and explaining that `no_window_match` implies the timestamp exceeded `duration_seconds`. Minor deduction: it says the window is 'about 2 minutes by default' while a 90-second half-window yields roughly 3 minutes of context, a small internal inconsistency.

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?

Specific verb and resource: fetches a focused ~2-minute window around one saved-video moment, and explicitly contrasts with returning 'a whole long video', which separates it from get_my_transcript. An agent can identify the tool's job without opening the schema.

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?

States the precondition clearly: takes the url and timestamp of a candidate returned by search_my_library, implying this tool follows a search step rather than starting one. It does not explicitly say when NOT to use it (e.g., when the user wants the full transcript), so it stops short of full alternative routing.

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

All SavedThat tools Inspect

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.