Skip to main content
Glama

Manage Creator documents

creator_document
Destructive

List durable Creator documents or one document's files; list a document's revisions ("history") or restore one ("restore" with revision); or reset one to an empty revision. Each creator_exec that changes the document saves a numbered revision. Restore saves that revision's content as a new one, so nothing is lost and creator_exec continues from it. Reset removes output files, cancels encodes and needs the caller's confirmation. To undo a change, restore; reset only when the user asks to wipe the scene.

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": {
      "action": "<action>"
    },
    "name": "creator_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
revisionNoAction "restore" only: the revision to bring back, e.g. "7".
documentIdNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations' blanket destructiveHint=true, the description breaks out which single action is destructive (reset removes output files, cancels encodes, requires caller confirmation) and which is safe (restore saves the old content as a new revision, so nothing is lost). It also discloses the revision-save behavior tied to creator_exec, which no structured field conveys.

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?

The action inventory is front-loaded, then behavior and the restore-vs-reset rule follow in a logical order, with no filler sentences. It is dense to the point of being packed—parenthetical action names interrupt the flow—but every sentence carries information.

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?

An output schema exists, so return values need not be explained, and the description covers all five actions plus the destructive/non-destructive distinction and revision semantics. The only real omission is what documentId selects (default document vs specific one), which matters for a multi-document tool.

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 only 33% and the action enum has no per-value descriptions in the schema, so the description carries real weight by explaining what "history", "restore" plus revision, and "reset" mean. The revision parameter's role is reinforced ("restore one ('restore' with revision)"). documentId remains unexplained in both schema and description, keeping it from a 5.

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?

The description names each operation concretely: listing documents or a document's files, listing revisions ("history"), restoring a revision ("restore"), and resetting to an empty revision. A verb+resource pair is clear for every action. It stops short of a 5 because it never distinguishes this tool from the sibling creator_docs, which plausibly overlaps on document listing.

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 maps action values to user intent ("history" for revisions, "restore" with a revision to bring one back) and gives an explicit when/when-not rule: "To undo a change, restore; reset only when the user asks to wipe the scene." Guidance for choosing between plain "list" and "files" is implied rather than stated, and no alternative/sibling is named.

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.