Skip to main content
Glama

Add an attached or linked file to the Playground canvas

playground_asset_import
Idempotent

Add one image (PNG, JPEG, WebP, ≤8 MB), video (MP4, ≤16 MB) or audio file (MP3 or WAV, ≤12 MB) to the canvas as a file node that can feed image and video generation. Pass exactly one source: file for a file the user attached in this chat (Berrys downloads it itself; no upload step), or url for a public HTTPS link. Bytes are checked and copied into project storage. Private, local and internal addresses are refused, and every redirect is rechecked. Free; revision checked and idempotent. Returns imported asset node details, revision and Playground URL.

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": {
      "projectId": "<projectId>",
      "expectedRevision": "<expectedRevision>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "playground_asset_import"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoPublic media URL to import as a canvas asset; for chat attachments use file instead. A public HTTPS link to the media. Omit when passing file.
fileNoA file the user attached in chat, as provided by the host. Omit when passing url.
kindNoMedia type to create or import, selected from the supported values.
projectIdYesID of the Playground project chosen for this task; obtain it from project creation, an explicit project link or current context.
idempotencyKeyYesUnique key for this request; reuse only when retrying the identical request after a lost response. Use a new key after quoting or changing inputs.
expectedRevisionYesCurrent canvas revision from canvas_read; on revision_conflict, read again and rebuild the change.

Output Schema

NameRequiredDescriptionDefault
kindYes
nodeIdYes
sha256No
mediaUrlYes
mimeTypeYes
replayedYes
revisionYes
canvasUrlYes
sourceUrlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the annotations (which only declare mutation, idempotency, openness, non-destructive), the description discloses concrete behavior: bytes are validated and copied into project storage, private/local/internal addresses are refused, every redirect is rechecked, the call is free, the revision is checked, and the return payload includes node details, revision and a Playground URL. This is strong added context, though it does not spell out the failure mode names beyond an implied revision conflict.

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?

Front-loaded with the action and accepted formats, then the source rule, then safety and return behavior – no filler sentences. It is dense, packing several clauses per sentence, which is efficient though slightly hard to scan in one pass.

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?

With an output schema, full parameter coverage, and annotations covering the safety profile, the description supplies everything else an agent needs: formats, size limits, source exclusivity, SSRF policy, idempotency, and revision-conflict handling. Nothing material for correct invocation 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 baseline is 3, but the description adds real meaning: the mutual-exclusivity rule (exactly one of file or url) is only stated in prose since the schema has no oneOf, and it ties size/format ceilings to the source kind. Per-parameter details like idempotencyKey reuse or expectedRevision conflict handling are left to the schema.

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?

The description states a specific verb (add/import) and resource (one media file as a file node on the canvas), enumerates accepted formats and size caps per media type, and clarifies the node can feed image and video generation. It is clearly distinguishable from siblings like playground_canvas_add_text or playground_drive_image_import without opening a 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?

It gives explicit source-selection guidance: use file for a chat attachment (Berrys downloads it; no upload step) and url for a public HTTPS link, and it mandates passing exactly one source. What it lacks is any comparison against sibling import paths (e.g., drive image import), so the agent gets clear context but no exclusion rules.

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.