Skip to main content
Glama

Translate Subtitles

translate_subtitles
Destructive

Translate an SRT without breaking its timing: call once for the numbered cues, translate them, then call with translations to write ..srt for chapters' subtitleTracks.

Instructions

Translate an SRT without breaking its timing: call once for the numbered cues, translate them, then call with translations to write ..srt for chapters' subtitleTracks.

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": {
      "input": "<input>"
    },
    "name": "translate_subtitles"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYesThe .srt to translate (e.g. from transcribe).
outputNoDefault: <input>.<language>.srt.
languageNoWith translations: ISO 639-2 code, e.g. "spa".
overwriteNoAllow replacing an existing output file.
translationsNoOne translated string per cue, in order. Omit to get the cues to translate.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.51.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already carry the risk profile (readOnly=false, destructiveHint=true, idempotent=false), and the description usefully confirms the write target ('<input>.<language>.srt') and the two-phase read-then-write behavior. However it omits behavioral consequences an agent would want: what happens when the output file already exists without overwrite, and how a translation-count mismatch against cue count is handled.

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 dense sentence that leads with the core constraint and then the call sequence; nothing is redundant. The compressed phrasing ('for chapters' subtitleTracks') is slightly awkward but still readable.

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 two-call, stateful translate-then-write tool with full schema coverage and no output schema, the description covers the essential non-obvious protocol and the output path. Remaining gaps are edge cases (overwrite failure mode, cue/translation count mismatch, returned cue format) that keep it from being fully complete.

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

Parameters3/5

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

Schema description coverage is 100%, so every parameter (input, output, language, overwrite, translations) is already documented in the schema, including defaults and the ISO 639-2 pattern. The description reinforces the workflow meaning of 'translations' by tying the second call to writing the file, but adds no syntax or format detail beyond the schema.

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 ('Translate an SRT') and immediately names the constraint that governs it ('without breaking its timing'). The two-phase cue/translation flow makes the tool's shape obvious, though it never names a sibling such as burn_subtitles to differentiate itself.

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 an explicit operational protocol: call once to get numbered cues, translate them, then call again with translations to write the file. That is concrete when-and-how guidance for a non-obvious two-call pattern. It stops short of stating when not to use it or how it relates to alternatives like burn_subtitles.

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