Skip to main content
Glama

Delete an output file

creator_delete_file
DestructiveIdempotent

Delete an output or media/ file by name. Deleting a file that is still encoding cancels the encode. Pass expectedJobId from a creator_download_file result to delete the file only while that job's export still holds the name, even after it completes. If another export replaced it, the call returns output_changed; check the export again instead of dropping expectedJobId.

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": {
      "file": "<file>"
    },
    "name": "creator_delete_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYesFile name passed to creator.render / creator.export, e.g. "hero.mp4".
documentIdNoDocument the file belongs to (default "default").
expectedJobIdNoDelete only while this job's export still holds the name, even after it completes.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: deleting a still-encoding file cancels the encode, and the expectedJobId condition protects against a race where another export replaced the name. The annotations only say destructive and idempotent; the description explains the actual side effects and the output_changed outcome.

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?

Four dense sentences, each carrying distinct information: target scope, encode-cancel side effect, expectedJobId purpose, and the output_changed recovery path. No filler, and the destructive scope is front-loaded.

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

Completeness5/5

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

Complete for a destructive delete with an output schema. The description covers the target file naming, the encode-cancellation behavior, the concurrency guard, and the failure path, so nothing an agent needs to call it correctly 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, but the description adds meaning beyond the schema by saying expectedJobId should come from a creator_download_file result and explaining the output_changed consequence. It adds more than the schema's own description of that field while not needing to re-explain file or documentId.

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 ('Delete an output or media/<name> file by name') and scopes the target file types clearly. An agent can distinguish this from creator_download_file or creator_save_to_workspace without opening any schema.

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 explicit conditional guidance: pass expectedJobId from a creator_download_file result to avoid deleting a replaced file, and on output_changed re-check the export instead of dropping the guard. The main gap is that it doesn't contrast with sibling tools for related operations, but the when-to-use logic for the tricky parameter is clearly spelled out.

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.