freeicon-mcp

ia_validate

Validates illustration scene-card SVGs for security, pure-vector self-containment, 4:3 canvas, and composition density; returns a normalized SVG with warnings.

Instructions

Validate an illustration scene-card SVG drawn per ia_generate: security filter, self-contained check (no /external refs — illustrations must be pure vector), canvas 4:3 check, composition density hints. Returns normalized SVG with warnings.

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": {
      "svg": "<svg>"
    },
    "name": "ia_validate"
  }
}

Input Schema

Name	Required	Description	Default
`svg`	Yes	The illustration SVG markup (root element must be <svg>)
`size`	No	Expected card width in px (default 480)

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.4Nov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the specific checks performed, the hard rejection rule (no <image>/external refs, pure vector only), and the return shape ('normalized SVG with warnings'). What it leaves out is whether failures are hard errors versus warnings, and whether the original input is ever mutated or rejected outright.

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?

A single front-loaded sentence with a compact colon-delimited list of checks plus a return clause — no filler. The clause is densely packed, requiring a second read, which keeps it just below top marks.

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 two-parameter validator with no output schema and no annotations, the description covers what is checked and what comes back, which is most of what an agent needs. The remaining gap is failure semantics — whether invalid input raises, returns errors alongside warnings, or returns the SVG unmodified.

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 coverage is 100%, so both parameters are already documented, establishing the baseline of 3. The description's 'canvas 4:3 check' loosely connects to the 'size' parameter but never explains that relationship or how size affects the aspect-ratio validation, so it adds little beyond 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 — validate an illustration scene-card SVG — and anchors it to the sibling that produces the input ('drawn per ia_generate'). The enumerated checks (security filter, self-contained, 4:3 canvas, density) make it unmistakably distinct from generic validators like lg_validate or g_validate.

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

Usage Guidelines4/5

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

The phrase 'drawn per ia_generate' establishes the intended workflow position: validate after generation. It gives clear context but names no exclusions, no when-not-to-use case, and does not say what the agent should do with the returned warnings.

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