Soleil Clusters

Upload image

upload_image

UPLOADS base64 image bytes and returns an image_key for add_cards. Charged to the board owner's storage; max 25MB. file_name keeps the file’s own name. For pictures on the web use import_urls instead; for video and other files, the REST API’s multipart upload.

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": {
      "board_id": "<board_id>",
      "data": "<data>",
      "content_type": "<content_type>"
    },
    "name": "upload_image"
  }
}

Input Schema

Name	Required	Description
`data`	Yes	The bytes, base64-encoded
`board_id`	Yes	The board charged for the storage
`file_name`	No	The file’s own name, e.g. diner_ext_dusk_04.jpg
`content_type`	Yes	The image’s real type

Output Schema

Name	Required	Description	Default
`width`	No
`height`	No
`file_name`	No
`image_key`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Goes beyond the annotations by disclosing two non-obvious side effects: the upload is billed to the board owner's storage and is capped at 25MB. This matters because idempotentHint=false means repeat calls create new stored objects, but the description does not address deduplication or failure 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short clauses, front-loaded with the core action and return value, then cost/size constraints, then alternatives. No filler sentences and nothing an agent needs is buried.

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

Completeness4/5

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

For a four-parameter upload tool with a full output schema and complete parameter descriptions, this covers purpose, storage billing, size limit, and escape hatches to sibling tools. Only behavior on failed or duplicate uploads is left unaddressed, which is minor given the annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters, including the enum of accepted content types. The description's notes on file_name and the storage-charging board largely restate the schema text ('The file's own name', 'The board charged for the storage'), adding little new meaning.

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 ('UPLOADS base64 image bytes'), names the return value ('image_key') and the downstream consumer ('for add_cards'), which tells an agent exactly where this fits in the workflow. It also explicitly separates itself from import_urls and from the REST multipart path.

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?

Gives explicit routing rules: use import_urls for pictures already on the web, and the REST multipart upload for video and other files. Both the when-to-use and when-not-to-use conditions are stated, with named alternatives.

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

All Soleil Clusters tools Inspect

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.