Skip to main content
Glama

Make an editing style

copy_style
DestructiveIdempotent

A reference's captions and pacing as a style (its edit: get_guide references). Link or file; none: upload link. clone: monthly copies included, then 25 credits. match: approximate, included.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "copy_style"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoOr an MP4, MOV or WebM on this computer.
modeNoclone (default): the deep copy. match: the fast, approximate copy.
nameNoThe style's name.
etagsNoPart ETags, in order.
formatNoThe reference: talking (a person on camera), faceless (a voice over pictures) or motion (graphics and music).
sha256NoIts sha256.
dry_runNotrue: answer the cost and start nothing.
referenceNoOr attached in ChatGPT.
staging_keyNoAfter sending.
operation_idNoSame id retries run once.
reference_urlNoA public Instagram, TikTok, X, Facebook, Loom or LinkedIn link to it.

Output Schema

NameRequiredDescriptionDefault
codeNo
costNo
errorNo
stateNo
statusNo
dry_runNo
messageNo
plan_idNo
style_idNo
video_idNo
availableNo
import_idNo
output_idNo
studio_urlNo
version_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / operation_id / pattern
      Removed value: -"^[a-zA-Z0-9_.:-]{1,100}$"
  2. Added
  3. Removed
  4. Changed10 schema fields changed
    • addedInput schema / properties / etags
      Added value: +{
      +  "description": "Part ETags, in order.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / file
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Or an MP4, MOV or WebM on this computer.",
      +  "properties": {
      +    "bytes": {
      +      "description": "Its size.",
      +      "minimum": 1,
      +      "type": "integer"
      +    },
      +    "name": {
      +      "description": "With extension.",
      +      "maxLength": 200,
      +      "minLength": 3,
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "name",
      +    "bytes"
      +  ],
      +  "type": "object"
      +}
    • changedInput schema / properties / format / description
      Previous value: -"What the reference is: talking (a person on camera), faceless (a voice over pictures) or motion (graphics and music)."New value: +"The reference: talking (a person on camera), faceless (a voice over pictures) or motion (graphics and music)."
    • changedInput schema / properties / mode / description
      Previous value: -"clone (default): deep, copies the reference's own motion and captions; slower; uses a monthly style copy, then credits. match: fast and approximate; included for every account."New value: +"clone (default): the deep copy. match: the fast, approximate copy."
    • changedInput schema / properties / name / description
      Previous value: -"A name for the new style."New value: +"The style's name."
    • changedInput schema / properties / operation_id / description
      Previous value: -"A retry with the same id runs once."New value: +"Same id retries run once."
    • changedInput schema / properties / reference / description
      Previous value: -"The reference video attached in ChatGPT, instead of a link."New value: +"Or attached in ChatGPT."
    • changedInput schema / properties / reference_url / description
      Previous value: -"A public link to the reference video (Instagram, TikTok, X, Facebook, Loom or LinkedIn). Send this or reference."New value: +"A public Instagram, TikTok, X, Facebook, Loom or LinkedIn link to it."
    • addedInput schema / properties / sha256
      Added value: +{
      +  "description": "Its sha256.",
      +  "type": "string"
      +}
    • addedInput schema / properties / staging_key
      Added value: +{
      +  "description": "After sending.",
      +  "type": "string"
      +}
  5. Changed1 schema field changed
    • changedInput schema / properties / operation_id / description
      Previous value: -"The same id on a retry runs it once; a new id is a new request."New value: +"A retry with the same id runs once."
  6. Changed5 schema fields changed
    • addedInput schema / properties / format / description
      Added value: +"What the reference is: talking (a person on camera), faceless (a voice over pictures) or motion (graphics and music)."
    • addedInput schema / properties / name / description
      Added value: +"A name for the new style."
    • changedInput schema / properties / operation_id / description
      Previous value: -"A stable ID for this authorized request. Preserve it on retries. Use a new ID only for a deliberate new request."New value: +"The same id on a retry runs it once; a new id is a new request."
    • addedInput schema / properties / reference / description
      Added value: +"The reference video attached in ChatGPT, instead of a link."
    • addedInput schema / properties / reference_url / description
      Added value: +"A public link to the reference video (Instagram, TikTok, X, Facebook, Loom or LinkedIn). Send this or reference."
  7. Changed1 schema field changed
    • addedInput schema / properties / mode
      Added value: +{
      +  "description": "clone (default): deep, copies the reference's own motion and captions; slower; uses a monthly style copy, then credits. match: fast and approximate; included for every account.",
      +  "enum": [
      +    "clone",
      +    "match"
      +  ],
      +  "type": "string"
      +}
  8. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "description": "Clypmint copy_style result. Error results carry error; successful requests expose the identifiers and state available for the next step. Signed media stays in private metadata.",
      +  "properties": {
      +    "available": {
      +      "type": "boolean"
      +    },
      +    "code": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "cost": {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    "dry_run": {
      +      "type": "boolean"
      +    },
      +    "error": {
      +      "type": "string"
      +    },
      +    "import_id": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "message": {
      +      "type": "string"
      +    },
      +    "output_id": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "plan_id": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "state": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "status": {
      +      "type": [
      +        "string",
      +        "integer",
      +        "null"
      +      ]
      +    },
      +    "studio_url": {
      +      "format": "uri",
      +      "type": "string"
      +    },
      +    "style_id": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "version_id": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "video_id": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
  9. Changed1 schema field changed
    • addedInput schema / properties / dry_run
      Added value: +{
      +  "description": "true: answer the cost and start nothing.",
      +  "type": "boolean"
      +}
  10. Changed1 schema field changed
    • addedInput schema / properties / format / type
      Added value: +"string"
  11. Changed1 schema field changed
    • addedInput schema / properties / format
      Added value: +{
      +  "enum": [
      +    "talking",
      +    "faceless",
      +    "motion"
      +  ]
      +}
  12. Changed1 schema field changed
    • addedInput schema / properties / operation_id
      Added value: +{
      +  "description": "A stable ID for this authorized request. Preserve it on retries. Use a new ID only for a deliberate new request.",
      +  "pattern": "^[a-zA-Z0-9_.:-]{1,100}$",
      +  "type": "string"
      +}
  13. First observed

TDQS

C2.9/5.0
Behavior3/5

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

Annotations declare destructiveHint=true, idempotentHint=true, and openWorldHint=true; the description never explains what the destructive aspect is (what a copy replaces or overwrites) or the retry/idempotency behavior. It does add genuinely new context beyond annotations: the clone cost model ('monthly copies included, then 25 credits') and the upload-link fallback when no reference exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but the structure is telegraphic colon-fragments ('Link or file; none: upload link') rather than a front-loaded statement of what the tool does. Size is appropriate; clarity and ordering are not.

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

Completeness2/5

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

For an 11-parameter, nested-object tool flagged destructive that spends credits, the description omits the reference-vs-file-vs-staging flow, the meaning of destructiveHint, and what a style actually captures beyond 'captions and pacing'. The output schema covers return values, but the operational and risk context an agent needs before invoking a destructive, credit-charging action is missing.

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, and the description clears that bar by adding pricing semantics for the mode enum ('clone: monthly copies included, then 25 credits. match: approximate, included') and the fallback path when no link/file is supplied. It still says nothing about the 11 parameters individually (etags, sha256, dry_run, operation_id), but the schema already documents those.

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 conveys the core idea — deriving a style (captions and pacing) from a reference — but only through a sentence fragment ('A reference's captions and pacing as a style'). The verb is implied rather than stated, and the parenthetical '(its edit: get_guide references)' is cryptic and doesn't cleanly differentiate this tool from siblings like adjust_style or browse_styles.

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?

'Link or file; none: upload link' gives input-channel guidance, and the clone/match pricing hints at a tradeoff, but there is no explicit statement of when to use this tool versus adjust_style, browse_styles, or apply_document. The mode tradeoff is left implicit rather than framed as a decision rule.

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