Skip to main content
Glama

Read a clip's captions

clip_captions

Retrieve the burned-in caption transcript and timestamps for a specific clip by its ID, so you can review or reuse the exact on-screen caption lines.

Instructions

The transcript of one clip, as burned-in caption lines with times.

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": {
      "clip_id": "<clip_id>"
    },
    "name": "clip_captions"
  }
}

Input Schema

NameRequiredDescriptionDefault
clip_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations and no output schema, the description carries the full burden, and it does disclose the one genuinely useful behavior: the return is timed caption lines rather than raw video or a file. It does not state that this is a read-only operation, what happens when clip_id is invalid, or whether the clip must have finished processing first.

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?

A single short sentence that front-loads the resource and then the payload shape, with no filler. The terseness is a limitation of content rather than structure, but the fragmentary phrasing leaves it without an explicit action verb.

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?

For a one-parameter read tool with no output schema, the description does what matters most by naming the return content and its timing dimension. It still leaves the agent guessing about the exact return structure (line objects vs a string), the meaning and provenance of clip_id, and how this differs from export_clip.

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?

There is only one parameter (clip_id) and the description at least ties it to 'one clip,' which is more than the bare schema offers at 0% coverage. It adds no format, source, or validity information beyond that, so it does not fully compensate for the undocumented parameter, but the tool is simple enough that the gap is small.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (the transcript of a single clip) and its shape (burned-in caption lines with times), which is enough to tell it apart from a list operation like list_clips. However, it is a noun phrase with no verb and never explicitly frames the operation as a read/fetch, and it draws no boundary against export_clip, which plausibly overlaps with caption retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this rather than export_clip, list_clips, or publish_plan. No prerequisites, no mention of what a clip_id must refer to, and no exclusions. The agent must infer intended usage entirely from the phrase describing the return value.

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