SavedThat

Get a moment from a creator's video

get_creator_moment

Read-onlyIdempotent

Fetch the transcript around one moment (about a minute and a half) in a creator's video, given the url and timestamp of a search_creator_videos candidate, so an idea can be read in context. Returns an excerpt only, never a whole transcript, plus a link to the exact second. When found is false, reason says which miss it was: not_a_creator_video means the url is not in a creator library at all, while no_transcript_at_timestamp means the video is here and only that second is uncovered, so another timestamp may well work.

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_creator_moment"
  }
}

Input Schema

Name	Required	Description	Default
`at`	Yes	Timestamp of the moment: seconds, or mm:ss / h:mm:ss.
`url`	Yes	Video URL from a search_creator_videos candidate.

Output Schema

Name	Required	Description
`at`	No
`url`	No
`found`	Yes
`range`	No
`title`	No
`reason`	No	Present only when found is false: why the moment could not be read.
`channel`	No
`creator`	No
`platform`	No
`deep_link`	No
`at_seconds`	No	With reason no_transcript_at_timestamp: the second that was asked for.
`transcript`	No
`thumbnail_url`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavior: the response is a bounded excerpt plus a deep link to the exact second, and `found=false` carries a `reason` whose two values are explained with different remedies. It stops short of describing excerpt boundaries or fallback behavior on the success path.

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?

Three sentences, front-loaded with what is fetched and how much, followed by the return shape, followed by the failure semantics. Every clause carries distinct information; nothing restates the title or the schema.

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 need not be fully described, yet the description still covers the two things an agent must act on: excerpt-only scope and the meaning of the `found`/`reason` failure states. For a two-parameter read tool with full annotation coverage, nothing needed for correct invocation 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 would be 3, but the description adds provenance semantics the schema lacks: `url` must come from a search_creator_videos candidate, and the timestamp identifies 'one moment' whose surrounding context is retrieved. That provenance rule is the key to correct invocation and is not in the schema.

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 and resource — fetch the transcript around one moment (~90 seconds) in a creator's video — and pins the scope with 'Returns an excerpt only, never a whole transcript.' It also identifies the upstream source of the inputs ('a search_creator_videos candidate'), which separates it from the generic get_moment sibling.

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?

The description clearly establishes the invocation context: it is a follow-up to a search_creator_videos candidate, taking that candidate's url and timestamp. It also gives recovery guidance for the failure path ('another timestamp may well work'), though it never explicitly contrasts against the get_moment sibling or states when not to use this tool.

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.