Skip to main content
Glama

lunara_upload_video

Reserve an upload slot and return the object key plus a signed URL per part. After uploading the bytes call lunara_finish_upload. Use this for a file you hold locally.

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": {
      "filename": "<filename>",
      "mime": "<mime>",
      "sizeBytes": "<sizeBytes>"
    },
    "name": "lunara_upload_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
mimeYesMIME type, e.g. audio/mpeg, video/mp4.
filenameYesOriginal filename, used for the download name.
projectIdNoProject to upload into. Omit to let Lunara reuse the most recent project for this organisation.
sizeBytesYesExact file size in bytes.
sourceLangNoWhat the speaker is actually speaking, in BCP-47 form: "yue-Hant-HK" Cantonese, "cmn-Hans-CN" Mandarin, "en-US" English, "ja-JP" Japanese, "ko-KR" Korean. Default "auto" (detect). This is INDEPENDENT of primaryLang/secondaryLang, which are the TEXT tracks you want back — e.g. English speech with primaryLang "zh-Hant" and secondaryLang "en" means "listen in English, give me Chinese and English subtitles".
spokenLangNoAlias of sourceLang — same value. Use whichever the other tools call it.
primaryLangNoWritten-track language. Default yue-Hant.
secondaryLangNoTranslated-track language. Default en.
secondaryLangsNoTranslation languages to produce in the same job (max 16). Merged with secondaryLang. Each one costs a separate translation pass; the speech is transcribed once.
clientOperationIdNoIdempotency key. Reuse the same value to retry without creating a second upload.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / secondaryLangs
      Added value: +{
      +  "description": "Translation languages to produce in the same job (max 16). Merged with secondaryLang. Each one costs a separate translation pass; the speech is transcribed once.",
      +  "items": {
      +    "enum": [
      +      "zh-Hant",
      +      "zh-CN",
      +      "yue-Hant",
      +      "en",
      +      "ja",
      +      "ko",
      +      "es",
      +      "fr",
      +      "de",
      +      "it",
      +      "pt",
      +      "pt-BR",
      +      "nl",
      +      "sv",
      +      "da",
      +      "no",
      +      "fi",
      +      "pl",
      +      "cs",
      +      "sk",
      +      "hu",
      +      "ro",
      +      "hr",
      +      "sl",
      +      "et",
      +      "lv",
      +      "lt",
      +      "ru",
      +      "uk",
      +      "bg",
      +      "sr",
      +      "ar",
      +      "he",
      +      "fa",
      +      "tr",
      +      "hi",
      +      "th",
      +      "vi",
      +      "id",
      +      "ms",
      +      "tl",
      +      "el",
      +      "sw"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 16,
      +  "type": "array"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / primaryLang / enum
      Previous value: -[
      -  "zh-Hant",
      -  "zh-Hans",
      -  "yue-Hant",
      -  "en",
      -  "ja",
      -  "ko",
      -  "es",
      -  "fr",
      -  "de",
      -  "it",
      -  "pt",
      -  "pt-BR",
      -  "nl",
      -  "sv",
      -  "da",
      -  "no",
      -  "fi",
      -  "pl",
      -  "cs",
      -  "sk",
      -  "hu",
      -  "ro",
      -  "hr",
      -  "sl",
      -  "et",
      -  "lv",
      -  "lt",
      -  "ru",
      -  "uk",
      -  "bg",
      -  "sr",
      -  "ar",
      -  "he",
      -  "fa",
      -  "tr",
      -  "hi",
      -  "th",
      -  "vi",
      -  "id",
      -  "ms",
      -  "tl",
      -  "el",
      -  "sw"
      -]New value: +[
      +  "zh-Hant",
      +  "zh-CN",
      +  "yue-Hant",
      +  "en",
      +  "ja",
      +  "ko",
      +  "es",
      +  "fr",
      +  "de",
      +  "it",
      +  "pt",
      +  "pt-BR",
      +  "nl",
      +  "sv",
      +  "da",
      +  "no",
      +  "fi",
      +  "pl",
      +  "cs",
      +  "sk",
      +  "hu",
      +  "ro",
      +  "hr",
      +  "sl",
      +  "et",
      +  "lv",
      +  "lt",
      +  "ru",
      +  "uk",
      +  "bg",
      +  "sr",
      +  "ar",
      +  "he",
      +  "fa",
      +  "tr",
      +  "hi",
      +  "th",
      +  "vi",
      +  "id",
      +  "ms",
      +  "tl",
      +  "el",
      +  "sw"
      +]
    • changedInput schema / properties / secondaryLang / enum
      Previous value: -[
      -  "zh-Hant",
      -  "zh-Hans",
      -  "yue-Hant",
      -  "en",
      -  "ja",
      -  "ko",
      -  "es",
      -  "fr",
      -  "de",
      -  "it",
      -  "pt",
      -  "pt-BR",
      -  "nl",
      -  "sv",
      -  "da",
      -  "no",
      -  "fi",
      -  "pl",
      -  "cs",
      -  "sk",
      -  "hu",
      -  "ro",
      -  "hr",
      -  "sl",
      -  "et",
      -  "lv",
      -  "lt",
      -  "ru",
      -  "uk",
      -  "bg",
      -  "sr",
      -  "ar",
      -  "he",
      -  "fa",
      -  "tr",
      -  "hi",
      -  "th",
      -  "vi",
      -  "id",
      -  "ms",
      -  "tl",
      -  "el",
      -  "sw"
      -]New value: +[
      +  "zh-Hant",
      +  "zh-CN",
      +  "yue-Hant",
      +  "en",
      +  "ja",
      +  "ko",
      +  "es",
      +  "fr",
      +  "de",
      +  "it",
      +  "pt",
      +  "pt-BR",
      +  "nl",
      +  "sv",
      +  "da",
      +  "no",
      +  "fi",
      +  "pl",
      +  "cs",
      +  "sk",
      +  "hu",
      +  "ro",
      +  "hr",
      +  "sl",
      +  "et",
      +  "lv",
      +  "lt",
      +  "ru",
      +  "uk",
      +  "bg",
      +  "sr",
      +  "ar",
      +  "he",
      +  "fa",
      +  "tr",
      +  "hi",
      +  "th",
      +  "vi",
      +  "id",
      +  "ms",
      +  "tl",
      +  "el",
      +  "sw"
      +]
  3. Changed2 schema fields changed
    • changedInput schema / properties / primaryLang / enum
      Previous value: -[
      -  "zh-Hant",
      -  "yue-Hant",
      -  "zh-CN",
      -  "en",
      -  "ja",
      -  "ko",
      -  "es",
      -  "fr",
      -  "de"
      -]New value: +[
      +  "zh-Hant",
      +  "zh-Hans",
      +  "yue-Hant",
      +  "en",
      +  "ja",
      +  "ko",
      +  "es",
      +  "fr",
      +  "de",
      +  "it",
      +  "pt",
      +  "pt-BR",
      +  "nl",
      +  "sv",
      +  "da",
      +  "no",
      +  "fi",
      +  "pl",
      +  "cs",
      +  "sk",
      +  "hu",
      +  "ro",
      +  "hr",
      +  "sl",
      +  "et",
      +  "lv",
      +  "lt",
      +  "ru",
      +  "uk",
      +  "bg",
      +  "sr",
      +  "ar",
      +  "he",
      +  "fa",
      +  "tr",
      +  "hi",
      +  "th",
      +  "vi",
      +  "id",
      +  "ms",
      +  "tl",
      +  "el",
      +  "sw"
      +]
    • changedInput schema / properties / secondaryLang / enum
      Previous value: -[
      -  "zh-Hant",
      -  "yue-Hant",
      -  "zh-CN",
      -  "en",
      -  "ja",
      -  "ko",
      -  "es",
      -  "fr",
      -  "de"
      -]New value: +[
      +  "zh-Hant",
      +  "zh-Hans",
      +  "yue-Hant",
      +  "en",
      +  "ja",
      +  "ko",
      +  "es",
      +  "fr",
      +  "de",
      +  "it",
      +  "pt",
      +  "pt-BR",
      +  "nl",
      +  "sv",
      +  "da",
      +  "no",
      +  "fi",
      +  "pl",
      +  "cs",
      +  "sk",
      +  "hu",
      +  "ro",
      +  "hr",
      +  "sl",
      +  "et",
      +  "lv",
      +  "lt",
      +  "ru",
      +  "uk",
      +  "bg",
      +  "sr",
      +  "ar",
      +  "he",
      +  "fa",
      +  "tr",
      +  "hi",
      +  "th",
      +  "vi",
      +  "id",
      +  "ms",
      +  "tl",
      +  "el",
      +  "sw"
      +]
  4. Changed2 schema fields changed
    • changedInput schema / properties / primaryLang / enum
      Previous value: -[
      -  "zh-Hant",
      -  "yue-Hant",
      -  "zh-CN",
      -  "en",
      -  "ja",
      -  "ko"
      -]New value: +[
      +  "zh-Hant",
      +  "yue-Hant",
      +  "zh-CN",
      +  "en",
      +  "ja",
      +  "ko",
      +  "es",
      +  "fr",
      +  "de"
      +]
    • changedInput schema / properties / secondaryLang / enum
      Previous value: -[
      -  "zh-Hant",
      -  "yue-Hant",
      -  "zh-CN",
      -  "en",
      -  "ja",
      -  "ko"
      -]New value: +[
      +  "zh-Hant",
      +  "yue-Hant",
      +  "zh-CN",
      +  "en",
      +  "ja",
      +  "ko",
      +  "es",
      +  "fr",
      +  "de"
      +]
  5. Changed2 schema fields changed
    • addedInput schema / properties / sourceLang
      Added value: +{
      +  "description": "What the speaker is actually speaking, in BCP-47 form: \"yue-Hant-HK\" Cantonese, \"cmn-Hans-CN\" Mandarin, \"en-US\" English, \"ja-JP\" Japanese, \"ko-KR\" Korean. Default \"auto\" (detect). This is INDEPENDENT of primaryLang/secondaryLang, which are the TEXT tracks you want back — e.g. English speech with primaryLang \"zh-Hant\" and secondaryLang \"en\" means \"listen in English, give me Chinese and English subtitles\".",
      +  "enum": [
      +    "auto",
      +    "yue-Hant-HK",
      +    "cmn-Hans-CN",
      +    "en-US",
      +    "ja-JP",
      +    "ko-KR"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / spokenLang
      Added value: +{
      +  "description": "Alias of sourceLang — same value. Use whichever the other tools call it.",
      +  "enum": [
      +    "auto",
      +    "yue-Hant-HK",
      +    "cmn-Hans-CN",
      +    "en-US",
      +    "ja-JP",
      +    "ko-KR"
      +  ],
      +  "type": "string"
      +}
  6. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare the write profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description doesn't need to re-litigate safety. It does add real behavioral value beyond them: this call only reserves a slot, returns a per-part signed URL, and is incomplete until lunara_finish_upload is called — a two-phase protocol an agent would otherwise miss. It stays silent on signed-URL expiry, size limits, and what happens to an abandoned slot.

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 short sentences, front-loaded with the action and return value, then the mandatory next step, then the disambiguation. Nothing is repeated from the schema and nothing is wasted.

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?

With no output schema, the description usefully tells the agent what comes back (object key plus signed URL per part) and that a second call is required. For a 10-parameter upload tool it is close to complete; only edge behavior (slot expiry, retry/idempotency, limits) is unstated, and some of that lives in the schema via clientOperationId.

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%, with enums and detailed language-track semantics already documented in the schema, including the sourceLang vs. primaryLang distinction. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

"Reserve an upload slot and return the object key plus a signed URL per part" states a specific verb, resource, and return shape, and "Use this for a file you hold locally" separates it from the URL-based ingest sibling (lunara_subtitle_from_url) without naming it. An agent can pick this tool over its siblings from the description alone.

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?

It gives a clear precondition (a file held locally, not a remote URL) and an explicit required follow-up step: "After uploading the bytes call lunara_finish_upload." The remote-URL alternative is implied rather than named, so the routing is slightly less airtight than a full when/when-not statement.

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