Skip to main content
Glama

MorphaReels

by ai.morphareels
OverviewDiscussionsAdmin

Upload image

upload_image
Destructive

Upload an image into a project from a public http(s) URL or a file attached in the chat, fetched server-side. Pass url for a public http(s) link, or file for a file the person attached in the chat (a host that supports file inputs, such as ChatGPT, fills file with a temporary download link itself; do not ask the person for a URL to something they have attached). The target is the URL you pass and nothing else: Morpha's Worker fetches it with a plain HTTP GET, following redirects, and identifies itself as "Morpha/1.0 (+https://morphareels.ai; hello@morphareels.ai)". No third-party API is involved. The worker downloads the .png/.jpg/.jpeg/.gif/.webp/.svg, stores it in the project's asset bucket under a new id, and returns { filename, name, sizeBytes, contentType, width, height }: pass the returned filename (the file's id, never shown to a person) to add_image_layer, and name is what people see; width and height are the picture's own pixel size (null when its header did not say), so size the layer from them or pass add_image_layer one side and let it keep the aspect. This tool does not search for images: pass a direct image file URL, such as one the person has given you, and respect the licence its source states. A url must be a direct, publicly-fetchable http(s) link (not an auth-walled page). SVGs are rejected if they carry a , an inline event handler, a , a javascript: URL, or an external resource reference — supply a static, self-contained SVG. Buffered in Worker memory, so capped at 16 MB. A file on the person's own disk is uploaded in the editor. Reference: https://morphareels.ai/docs/tools#uploadimageurl-file-name

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoDirect, publicly-fetchable http(s) URL of the image file (.png/.jpg/.jpeg/.gif/.webp/.svg). Pass either this or `file`.
fileNoA file the person attached in the chat (a host that supports file inputs, such as ChatGPT, fills this itself; do not type it). Pass either this or `url`.
nameNoOptional display name, what people see (e.g. Logo.png). Defaults to the attached file's name or the URL's file name. It never decides where the file is stored.
projectIdYesProject to add the image to.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesWhether the call succeeded.
dataNoThe payload, shaped by the tool.
noteNoWhat to do next when not ready.
errorNoWhy it failed.
statusNoFor cache-backed readers: whether the answer was ready.
editorUrlNoOpens this project in the editor.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / file
      Added value: +{
+  "description": "A file the person attached in the chat (a host that supports file inputs, such as ChatGPT, fills this itself; do not type it). Pass either this or `url`.",
+  "properties": {
+    "download_url": {
+      "description": "Temporary URL the host serves the file at.",
+      "type": "string"
+    },
+    "file_id": {
+      "description": "The host's id for the file.",
+      "type": "string"
+    },
+    "file_name": {
+      "description": "The file's own name, when the host knows it.",
+      "type": "string"
+    },
+    "mime_type": {
+      "description": "The file's media type, when the host knows it.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "download_url",
+    "file_id"
+  ],
+  "type": "object"
+}
    • changedInput schema / properties / name / description
      Previous value: -"Optional display name, what people see (e.g. Logo.png). Defaults to the URL's file name. It never decides where the file is stored."New value: +"Optional display name, what people see (e.g. Logo.png). Defaults to the attached file's name or the URL's file name. It never decides where the file is stored."
    • changedInput schema / properties / url / description
      Previous value: -"Direct, publicly-fetchable http(s) URL of the image file (.png/.jpg/.jpeg/.gif/.webp/.svg)."New value: +"Direct, publicly-fetchable http(s) URL of the image file (.png/.jpg/.jpeg/.gif/.webp/.svg). Pass either this or `file`."
    • changedInput schema / required
      Previous value: -[
-  "projectId",
-  "url"
-]New value: +[
+  "projectId"
+]
  2. Changed2 schema fields changed
    • removedInput schema / properties / filename
      Removed value: -{
-  "description": "Optional stored filename (.png/.jpg/.jpeg/.gif/.webp/.svg). Defaults to the basename of the URL path; sanitised to lowercase a-z0-9._-.",
-  "type": "string"
-}
    • addedInput schema / properties / name
      Added value: +{
+  "description": "Optional display name, what people see (e.g. Logo.png). Defaults to the URL's file name. It never decides where the file is stored.",
+  "type": "string"
+}
  3. Changed2 schema fields changed
    • removedInput schema / properties / anonymousToken
      Removed value: -{
-  "description": "The token create_anonymous_account returned. This connection has no Morpha key, so every call carries it.",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "projectId",
-  "url",
-  "anonymousToken"
-]New value: +[
+  "projectId",
+  "url"
+]
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "description": "The result envelope every Morpha tool returns.",
+  "properties": {
+    "data": {
+      "description": "The payload, shaped by the tool.",
+      "type": [
+        "object",
+        "array",
+        "string",
+        "number",
+        "boolean",
+        "null"
+      ]
+    },
+    "editorUrl": {
+      "description": "Opens this project in the editor.",
+      "type": "string"
+    },
+    "error": {
+      "description": "Why it failed.",
+      "type": "string"
+    },
+    "note": {
+      "description": "What to do next when not ready.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether the call succeeded.",
+      "type": "boolean"
+    },
+    "status": {
+      "description": "For cache-backed readers: whether the answer was ready.",
+      "enum": [
+        "ready",
+        "not-ready"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}
  5. Changed2 schema fields changed
    • addedInput schema / properties / anonymousToken
      Added value: +{
+  "description": "The token create_anonymous_account returned. This connection has no Morpha key, so every call carries it.",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "projectId",
-  "url"
-]New value: +[
+  "projectId",
+  "url",
+  "anonymousToken"
+]
  6. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover only readOnly/openWorld/destructive hints; the description adds substantial behavior the annotations cannot express: server-side fetch semantics (plain HTTP GET, follows redirects, a named User-Agent), 'No third-party API is involved', storage into the project's asset bucket under a new id, a 16 MB cap imposed by Worker-memory buffering, and explicit SVG rejection rules (script tags, event handlers, foreignObject, javascript: URLs, external references).

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 core verb, resource and source options are front-loaded in the first sentence, and most of the length is load-bearing (limits, SVG rules, return routing). It loses a point for a single run-on paragraph and some restatement, e.g. the 'direct, publicly-fetchable http(s)' requirement appears in both the first and second half, and the trailing docs URL adds little for an agent.

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?

Despite an output schema existing, the description still helps by naming the returned fields and telling the agent to pass `filename` (not `name`) into add_image_layer and to use `width`/`height` for sizing. Combined with the size cap, accepted formats and SVG rejection conditions, an agent has everything needed to invoke this correctly and handle the common failure modes.

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 3 is the baseline, but the description meaningfully enriches semantics beyond the schema: `file` is host-populated and must not be typed by the agent, `url` must be a direct publicly-fetchable link rather than an auth-walled page, and `name` is display-only and 'never decides where the file is stored.' That clarification of intent goes past the field-level text, though it does not fully annotate every field.

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 first sentence names a specific verb and resource with explicit source scope ('Upload an image into a project from a public http(s) URL or a file attached in the chat, fetched server-side'), and later sentences actively distinguish it from siblings by naming add_image_layer as the consumer of the returned filename and stating 'This tool does not search for images.' An agent can separate it from add_image_layer and upload_audio 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit conditional routing: 'Pass `url` for a public http(s) link, or `file` for a file the person attached in the chat,' plus the anti-pattern 'do not ask the person for a URL to something they have attached.' It also states what the tool is not for ('does not search for images') and where an out-of-scope case belongs ('A file on the person's own disk is uploaded in the editor').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All MorphaReels toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources