upload_imageStore a picture (PNG, JPEG, GIF or WEBP, up to 25 MB, base64-encoded) and get its "src" for an image block or a slide background. Big pictures are scaled down to 2560 px.
| Name | Required | Description | Default |
|---|---|---|---|
| data_base64 | Yes | The file, base64 (a data: URL prefix is allowed). |
| Name | Required | Description | Default |
|---|---|---|---|
| h | No | ||
| w | No | ||
| src | Yes | Use it as "src" of an image block or background. | |
| url | No |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "h": {
+ "type": "integer"
+ },
+ "src": {
+ "description": "Use it as \"src\" of an image block or background.",
+ "type": "string"
+ },
+ "url": {
+ "type": "string"
+ },
+ "w": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "src"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=false. The description adds genuinely new behavioral context: accepted formats (PNG/JPEG/GIF/WEBP), a 25 MB ceiling, base64 encoding, and the non-obvious transformation that large images are downscaled to 2560 px. It omits auth/error behavior, so it stops short of a 5.
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?
Two sentences, front-loaded with what is stored and what is returned, followed by the format/size constraints and the downscaling caveat. No filler and nothing repeated from structured fields.
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 single-parameter upload with an output schema covering the returned src, the description supplies everything an agent needs: input format, size cap, encoding, and the resolution transformation. Nothing required 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.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and there is only one parameter, so the baseline is 3; the schema already documents the base64 payload and the allowed data: URL prefix. The description nevertheless adds constraints absent from the schema (format whitelist, 25 MB size limit), which materially affects how the agent must prepare the value.
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?
Specific verb (store/upload) plus resource (a picture) plus the outcome (its "src" for an image block or slide background). No sibling tool performs image uploads, so this definition is unambiguous against the rest of the toolset without needing to name an alternative.
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?
The description implies the use case by saying the returned src feeds an image block or slide background, which tells the agent roughly when to reach for it. However, it never states prerequisites or when-not to use it (e.g. whether it must precede edit_blocks or add_slide), so usage is only implied rather than explicit.
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.