Skip to main content
Glama

Save a selected image in VoxTale

import_asset_file

Save one JPEG, PNG or WebP file explicitly selected or uploaded by the user in ChatGPT (max 20 MB), as a face photo or optional style reference. Accepts OpenAI file params only. Does not generate images. Do not repeat on an uncertain result; refresh the image picker first.

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": {
      "file": "<file>"
    },
    "name": "import_asset_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYes
roleNoface

Output Schema

NameRequiredDescriptionDefault
roleYes
assetIdYes
filenameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-idempotent, non-destructive, open-world behavior; the description adds genuinely new operational context on top: a 20 MB size limit, accepted MIME types, the fact that only OpenAI file params are accepted, and an explicit warning not to retry blindly on an uncertain result. The retry caveat is especially valuable given idempotentHint=false, since it prevents duplicate imports. It does not say what happens if the same file is imported twice.

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?

Three short sentences with the core action and constraints front-loaded and no filler. The phrase 'Accepts OpenAI file params only' is slightly opaque and assumes prior knowledge of that payload shape, which costs a bit of clarity.

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?

An output schema exists, so return values need not be described, and annotations cover the safety profile. For a two-parameter write tool the description covers purpose, size/format limits, role meaning, and retry behavior; the main residual gap is the undocumented nested file fields and any duplicate-import semantics.

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 0% with a nested file object containing four undocumented fields (file_id, download_url, file_name, mime_type), so the description must carry the load. It does explain the role enum in natural language ('face photo or optional style reference') and constrains the file type and size, but it leaves the required nested fields and their expected format unexplained beyond the vague phrase 'Accepts OpenAI file params only'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Save one JPEG, PNG or WebP file ... as a face photo or optional style reference') plus hard constraints (20 MB cap, OpenAI file params only). It also carves out a negative boundary ('Does not generate images'), which helps separate it from the generation siblings, but it never names the adjacent upload-flow tools, so the differentiation is only partial.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

There is a real precondition ('explicitly selected or uploaded by the user in ChatGPT') and a useful retry rule ('Do not repeat on an uncertain result; refresh the image picker first'), which is more than most definitions offer. However, it never explains when to use this versus create_asset_upload or complete_asset_upload, so the agent has to guess at the intended flow.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources