Skip to main content
Glama

search_transcript

Search a video’s subtitles for a phrase and return matches with timestamps and speakers. Use it to answer what’s said or find the moment to jump to.

Instructions

Search the currently playing file's subtitles for a phrase and return every match with its timestamp and speaker (if known). Works with loaded subtitle files, sidecar .srt/.vtt/.ass/.ssa files, embedded text tracks, and subtitles you generated with generate_subtitles. Use this to answer questions about what is said in a video, or to find the moment to jump to. Case-insensitive substring match, not regex.

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": {
      "query": "<query>"
    },
    "name": "search_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoOptional path to a video or subtitle file; defaults to the playing file
limitNoMaximum matches to return (default 20, max 200)
queryYesPhrase to look for
speakerNoOptional speaker filter (case-insensitive substring match)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
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 reasonably well: it enumerates supported sources (loaded subtitle files, sidecar .srt/.vtt/.ass/.ssa, embedded tracks, generated subtitles) and specifies case-insensitive substring matching rather than regex. It omits what happens when no subtitles exist for the file, which is the main behavioral gap.

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 tight sentences, front-loaded with the core action and return values, then sources, then matching semantics. No filler and nothing that duplicates the schema verbatim.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter read tool with no output schema, the description supplies enough: what is searched, what comes back, and how matching works. The remaining gap is edge-case behavior when the file has no subtitles or when the file parameter points at an unloaded path.

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, but the description adds real meaning beyond the schema by clarifying that the match is case-insensitive substring, not regex — a distinction that changes how an agent should phrase a query. The speaker filter and limit default are left to 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 (search the currently playing file's subtitles for a phrase) and even describes the return shape (every match with timestamp and speaker). The scope wording ('currently playing file') separates it from library-wide transcript search siblings without needing their names.

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?

Gives two concrete use cases: answering questions about what is said in a video, and finding a moment to jump to. It does not state when to prefer library_transcript_search or transcript_get instead, so the alternative-selection guidance is implicit rather than explicit.

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

Deploy Server

Other Tools