Fashio AI

Upload an image to Fashio

upload_image

Uploads one image you have as base64 bytes and returns {id, url}; pass that url into any images.* field of create_generation, create_catalog_job or create_template_set. Use this for an image that exists only in the conversation or on your machine; skip it when the image already has a public URL (pass that URL directly). JPEG/PNG/WebP only, max 8 MB: 413 if larger, 415 if the bytes are not a recognised image (checked by file signature, not by format). Free (no diamonds). Needs a valid Fashio API key (Bearer); every call counts toward the key's daily request cap (429 when reached, 401 for a missing or revoked key).

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": {
      "base64": "<base64>",
      "format": "<format>"
    },
    "name": "upload_image"
  }
}

Input Schema

Name	Required	Description	Default
`base64`	Yes	The image file's bytes, base64-encoded, without a 'data:image/...;base64,' prefix. Max 8 MB once decoded.
`format`	Yes	File type of the bytes: jpg \| jpeg \| png \| webp. Sets the upload's Content-Type; the server still verifies the real format.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 8, 2026

changedInput schema / properties / base64 / description

Previous value: -"Base64-encoded image bytes (no data: prefix)."New value: +"The image file's bytes, base64-encoded, without a 'data:image/...;base64,' prefix. Max 8 MB once decoded."

addedInput schema / properties / format / description

Added value: +"File type of the bytes: jpg | jpeg | png | webp. Sets the upload's Content-Type; the server still verifies the real format."

First observedNov 8, 2026

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses accepted types, the 8 MB limit, the specific error codes (413 size, 415 unrecognised image, 401 auth, 429 daily cap), that validation is by file signature rather than the declared `format`, that the call is free, and that it consumes the key's daily request quota. That is unusually complete behavioral context for a mutation/upload tool.

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 purpose and return value, then destinations, then the when-not rule, then constraints and error codes — a sensible ordering with no filler sentences. It is delivered as one dense paragraph, so the error/auth/cost tail runs together and would read better split.

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?

For a two-parameter upload with no output schema, the description covers return shape, downstream consumption, format/size limits, error semantics, and auth/quota expectations. Nothing an agent needs to call it correctly or predict failure 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 already 100%, so the baseline is 3; the description adds meaning beyond it by warning that `format` sets Content-Type but does not determine validity ('checked by file signature, not by `format`'), which is a real invocation trap. It does not restate the no-data-prefix rule, which stays in 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?

States a specific verb and resource ('Uploads one image ... as base64 bytes'), names the exact return shape ('returns {id, url}'), and immediately tells the agent where the result is consumed (images.* fields of create_generation, create_catalog_job, create_template_set). This clearly separates it from the create_* siblings without opening their schemas.

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 an explicit inclusion rule ('an image that exists only in the conversation or on your machine') and an explicit exclusion with the alternative action ('skip it when the image already has a public URL (pass that URL directly)'). The when-not and the substitute behavior are both spelled out.

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

All Fashio AI 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.