Skip to main content
Glama

Get Transcript Segment

get_transcript_segment
Read-onlyIdempotent

Get transcript turns overlapping an optional window of at most five minutes, with exact timestamps. Defaults to 00:00–03:00 so the first call stays within the response limit.

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": {
      "episode": "<episode>"
    },
    "name": "get_transcript_segment"
  }
}

Input Schema

NameRequiredDescriptionDefault
end_msNo
episodeYes
start_msNo

Output Schema

NameRequiredDescriptionDefault
dataYes
metaYes
operationYes
schema_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / meta / properties / clip_catalog
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "catalog_id": {
      +      "const": "htrtf-youtube-clips",
      +      "type": "string"
      +    },
      +    "catalog_sha256": {
      +      "pattern": "^[a-f0-9]{64}$",
      +      "type": "string"
      +    },
      +    "catalog_version": {
      +      "maxLength": 80,
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    "generated_at": {
      +      "format": "date-time",
      +      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "catalog_id",
      +    "catalog_version",
      +    "catalog_sha256",
      +    "generated_at"
      +  ],
      +  "type": "object"
      +}
  2. Changed36 schema fields changed
    • addedInput schema / properties / end_ms / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / start_ms / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / data / properties / end_ms / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / data / properties / start_ms / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / data / properties / turns / items / properties / citation / properties / end_ms / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / data / properties / turns / items / properties / citation / properties / start_ms / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / data / properties / turns / items / properties / end_ms / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / data / properties / turns / items / properties / start_ms / maximum
      Added value: +9007199254740991
    • removedOutput schema / properties / meta / properties / artifact_manifest_sha256 / $ref
      Removed value: -"#/properties/meta/properties/manifest_sha256"
    • addedOutput schema / properties / meta / properties / artifact_manifest_sha256 / pattern
      Added value: +"^[a-f0-9]{64}$"
    • addedOutput schema / properties / meta / properties / artifact_manifest_sha256 / type
      Added value: +"string"
    • removedOutput schema / properties / meta / properties / artifact_sha256 / $ref
      Removed value: -"#/properties/meta/properties/manifest_sha256"
    • addedOutput schema / properties / meta / properties / artifact_sha256 / pattern
      Added value: +"^[a-f0-9]{64}$"
    • addedOutput schema / properties / meta / properties / artifact_sha256 / type
      Added value: +"string"
    • removedOutput schema / properties / meta / properties / release_sha256 / $ref
      Removed value: -"#/properties/meta/properties/manifest_sha256"
    • addedOutput schema / properties / meta / properties / release_sha256 / pattern
      Added value: +"^[a-f0-9]{64}$"
    • addedOutput schema / properties / meta / properties / release_sha256 / type
      Added value: +"string"
    • removedOutput schema / properties / meta / properties / rights / properties / policy_url / $ref
      Removed value: -"#/properties/meta/properties/canonical_url"
    • addedOutput schema / properties / meta / properties / rights / properties / policy_url / format
      Added value: +"uri"
    • addedOutput schema / properties / meta / properties / rights / properties / policy_url / maxLength
      Added value: +2048
    • addedOutput schema / properties / meta / properties / rights / properties / policy_url / type
      Added value: +"string"
    • removedOutput schema / properties / meta / properties / snapshot_sha256 / $ref
      Removed value: -"#/properties/meta/properties/manifest_sha256"
    • addedOutput schema / properties / meta / properties / snapshot_sha256 / pattern
      Added value: +"^[a-f0-9]{64}$"
    • addedOutput schema / properties / meta / properties / snapshot_sha256 / type
      Added value: +"string"
    • removedOutput schema / properties / meta / properties / surface_version / properties / artifact_manifest_hash / $ref
      Removed value: -"#/properties/meta/properties/manifest_sha256"
    • addedOutput schema / properties / meta / properties / surface_version / properties / artifact_manifest_hash / pattern
      Added value: +"^[a-f0-9]{64}$"
    • addedOutput schema / properties / meta / properties / surface_version / properties / artifact_manifest_hash / type
      Added value: +"string"
    • removedOutput schema / properties / meta / properties / surface_version / properties / content_version / $ref
      Removed value: -"#/properties/meta/properties/content_version"
    • addedOutput schema / properties / meta / properties / surface_version / properties / content_version / pattern
      Added value: +"^sha256:[a-f0-9]{64}$"
    • addedOutput schema / properties / meta / properties / surface_version / properties / content_version / type
      Added value: +"string"
    • removedOutput schema / properties / meta / properties / surface_version / properties / transcript_version / $ref
      Removed value: -"#/properties/meta/properties/content_version"
    • addedOutput schema / properties / meta / properties / surface_version / properties / transcript_version / pattern
      Added value: +"^sha256:[a-f0-9]{64}$"
    • addedOutput schema / properties / meta / properties / surface_version / properties / transcript_version / type
      Added value: +"string"
    • removedOutput schema / properties / meta / properties / transcript_version / $ref
      Removed value: -"#/properties/meta/properties/content_version"
    • addedOutput schema / properties / meta / properties / transcript_version / pattern
      Added value: +"^sha256:[a-f0-9]{64}$"
    • addedOutput schema / properties / meta / properties / transcript_version / type
      Added value: +"string"
  3. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the description only needs to add context — and it does, disclosing the five-minute window cap and an implicit response-size limit that shapes the default. It stops short of saying what happens at window boundaries or whether overlapping turns can be returned twice across calls.

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?

Two sentences, zero filler, with the core capability front-loaded and the default plus its rationale following immediately. Nothing could be removed without losing information.

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?

Return values need not be explained since an output schema exists, and the safety profile is covered by annotations. But for a three-parameter tool with 0% schema coverage, omitting the millisecond unit convention, the episode parameter, and how to page beyond the default window leaves real gaps for an agent trying to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, yet it never names or explains any of the three parameters. Worse, it expresses the window as '00:00–03:00' (mm:ss) while start_ms/end_ms are integer millisecond fields, and the required 'episode' identifier is not mentioned at all — an agent must reverse-engineer units and roles from the schema alone.

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?

States a specific verb and resource ('Get transcript turns') plus the scoping concept (an optional overlapping window) and the exact-timestamp guarantee. It is clearly distinct from the sibling tools (clips, episode metadata, flashcards, reading trail), though it never names a sibling to route against.

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?

It gives useful operational guidance: the window is optional, capped at five minutes, and defaults to 00:00–03:00 so the first call stays inside the response limit. However, it does not say when to reach for this tool versus get_episode or get_clip, nor how to continue past the first five minutes.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources