upload_assetPlace the user's own image or SVG file.
| Name | Required | Description | Default |
|---|---|---|---|
| x | No | ||
| y | No | ||
| as | No | ||
| fit | No | ||
| url | No | ||
| name | No | ||
| scrim | No | ||
| width | No | ||
| height | No | ||
| purpose | No | ||
| artboard | No | ||
| asset_id | No | ||
| data_url | No | ||
| shape_ids | No | ||
| tile_size | No | ||
| corner_radius | No |
Changes observed during successful MCP inspections.
Input schema / $schemaRemoved value: -"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / artboard / anyOfPrevious value: -[
- {
- "maximum": 9007199254740991,
- "minimum": 0,
- "type": "integer"
- },
- {
- "maxLength": 120,
- "type": "string"
- }
-]New value: +[
+ {
+ "type": "integer"
+ },
+ {
+ "type": "string"
+ }
+]Input schema / properties / as / descriptionRemoved value: -"SVG only: shapes (default, editable) or image (one picture). Rasters are always images."Input schema / properties / asset_id / descriptionRemoved value: -"ast_... from POST /api/v1/assets or an earlier upload_asset reply. Expires after 24 h."Input schema / properties / asset_id / patternRemoved value: -"^ast_[a-z2-7]{16}$"Input schema / properties / corner_radius / descriptionRemoved value: -"Images only."Input schema / properties / corner_radius / minimumRemoved value: -0Input schema / properties / data_url / descriptionRemoved value: -"data:image/png;base64,... (or image/svg+xml). Small files only; use asset_id for anything over a few KB."Input schema / properties / data_url / maxLengthRemoved value: -5592470Input schema / properties / fit / descriptionRemoved value: -"Images only. Default cover."Input schema / properties / height / exclusiveMinimumRemoved value: -0Input schema / properties / name / maxLengthRemoved value: -120Input schema / properties / purpose / descriptionRemoved value: -"artwork (default): place the user's file. pattern_tile: an SVG tile that repeats as the fill of shape_ids (patterns and textures only)."Input schema / properties / scrim / anyOfPrevious value: -[
- {
- "type": "boolean"
- },
- {
- "additionalProperties": false,
- "properties": {
- "color": {
- "maxLength": 64,
- "type": "string"
- },
- "direction": {
- "enum": [
- "bottom",
- "top",
- "left",
- "right"
- ],
- "type": "string"
- },
- "opacity": {
- "maximum": 1,
- "minimum": 0,
- "type": "number"
- },
- "start": {
- "maximum": 0.95,
- "minimum": 0,
- "type": "number"
- }
- },
- "type": "object"
- }
-]New value: +[
+ {
+ "type": "boolean"
+ },
+ {
+ "description": "Scrim options: docs {tool}.",
+ "type": "object"
+ }
+]Input schema / properties / scrim / descriptionRemoved value: -"Images only: a gradient wash so text over the picture reads."Input schema / properties / shape_ids / descriptionRemoved value: -"pattern_tile only: the shapes to fill with the repeating tile."Input schema / properties / shape_ids / items / maxLengthRemoved value: -128Input schema / properties / shape_ids / maxItemsRemoved value: -200Input schema / properties / shape_ids / minItemsRemoved value: -1Input schema / properties / tile_size / descriptionRemoved value: -"pattern_tile only: the tile's width in document units (height follows the SVG's aspect). Default: the SVG's own width, capped at 128."Input schema / properties / tile_size / maximumRemoved value: -128Input schema / properties / tile_size / minimumRemoved value: -2Input schema / properties / url / descriptionRemoved value: -"Direct https link to a PNG, JPEG, WebP, GIF or SVG file (not a web page)."Input schema / properties / url / formatRemoved value: -"uri"Input schema / properties / url / maxLengthRemoved value: -2048Input schema / properties / width / exclusiveMinimumRemoved value: -0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the safety profile is covered structurally. The description adds only the 'user's own' sourcing nuance and says nothing about the destructive consequences of placement, how url/data_url/asset_id differ as sources, or what happens when placement overlaps existing shapes.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is a single short sentence with no padding, but the brevity comes from under-specification rather than economy; it front-loads nothing about the 16-parameter surface an agent must fill in.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 16-parameter, destructive, non-idempotent mutation with no output schema and no schema descriptions, the description is far from sufficient. An agent could not correctly supply placement coordinates, source selection, or fitting behavior from this text.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Sixteen parameters with 0% schema description coverage and no parameter discussion whatsoever in the description. Nothing explains x/y positioning, fit cover vs contain, 'as' auto/shapes/image, purpose artwork vs pattern_tile, tile_size, corner_radius, scrim, or the three mutually exclusive asset sources.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a verb (place) and resource (image or SVG file) and adds the useful qualifier 'the user's own', distinguishing it from stock sources. But it does not distinguish itself from close siblings like place_image, set_reference_image, add_texture, or get_assets, so an agent cannot confidently pick between them from the description alone.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no indication of when to use this versus place_image, search_photos, get_assets, or add_texture, and no mention of prerequisites such as needing an open project or active artboard. Usage must be inferred entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.