no-api-media

Overview Schema Source Related Servers Discussions Admin

Eye-catch audit of a finished image

design_audit

Score a generated image 0-5 on eight design criteria to get a ship or revise verdict, its weakest points and the exact fix for each.

Instructions

After you have LOOKED at a generated image, score it 0 to 5 on each criterion (focal-point, thumbnail, hierarchy, palette, topic-cues, brand-presence, text-accuracy, not-template) and pass the scores here. Returns ship or revise, the weakest points and the exact fix for each. Call with no scores to get the criteria. Be harsh: a generic, flat or template-looking result scores 2 or 3. Pass asset_type so the server learns what usually goes wrong and warns you up front next time. Pass file (the draft inside .ai-media) so a revise marks it rejected, which lets it be cleaned up later, and a ship marks it shortlisted. Pass style.tier and style.look (whatever you actually passed to design_brief) so the server can remember, once enough drafts have shipped, which tier and look tend to work for this asset type and suggest it by default next time.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "design_audit"
  }
}

Input Schema

Name	Required	Description
`file`	No	The draft you scored, relative to the project, e.g. .ai-media/codex/banner.png. It's also measured, and the measurements can cap your scores
`style`	No	The style you actually used for this draft, so a shipped result can be remembered
`scores`	No
`asset_type`	No
`planned_edges`	No	Edges left calm on purpose for text, so they don't count as empty bands

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.4.1Oct 25, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the burden well: it discloses side effects (revise marks rejected, ship marks shortlisted), server learning behavior, and that measurements can cap scores. Gaps remain around auth, error cases, and durability of the shortlist/reject state, but the key behaviors are disclosed.

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 the core action and return values, then the side-effect guidance. The back half is dense but each sentence carries distinct information; only the learning-loop explanation drifts toward verbosity.

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?

Given a 5-param nested tool with no output schema and no annotations, the description covers the workflow (look, score, submit), returns, and side effects. Missing only return-shape details for revises beyond 'weakest points and exact fix' and behavior for planned_edges.

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?

At 60% schema coverage, the description adds real meaning: it explains the file lifecycle consequence, why asset_type and style matter, and provides the eight criterion keys expected in scores. It doesn't explain planned_edges or why scores is free-form/additionalProperties, which is a notable omission but not fatal.

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: score a generated image 0-5 on eight named criteria and get a ship/revise verdict. The named criteria and return values distinguish it clearly from siblings like composition_check or design_feedback.

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?

Explicitly says to call after LOOKING at the image, and that calling with no scores returns the criteria. It also states what to pass and why (asset_type for learning, file for lifecycle marking, style so defaults can be suggested), which is strong when/when-not guidance.

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