A2UI Atomic Catalog

distill_document

Read-only

Compile a training.md / roadmap markdown document into a live interactive A2UI app — DETERMINISTIC parser, no model involved. Fact sheet: input is MARKDOWN following the training-md contract (frontmatter id/domain/name/source/license + a # Steps section); the text transits to the catalog's stateless parser service for the duration of the call and is NOT stored; lint errors come back as a structured report (fix and re-call). On success the result IS the compiled surface — MCP Apps hosts paint it in the view; other hosts can pass the returned payload to preview_url for a link.

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": {
      "markdown": "<markdown>"
    },
    "name": "distill_document"
  }
}

Input Schema

Name	Required	Description	Default
`domain`	No	parse contract to apply (default training)
`markdown`	Yes	the full markdown document, frontmatter included

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Beyond the annotations it discloses genuinely useful behavior: deterministic parsing with no model, that the text transits a stateless parser service and is not stored, and that failures arrive as a structured lint report requiring a corrected re-call. One mild tension: 'DETERMINISTIC parser' reads as repeatable, while idempotentHint is false — plausibly because each success yields a new surface, but the description does not reconcile that.

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, then a labeled 'Fact sheet' covering input contract, data handling, error behavior, and success hand-off — efficient for the amount of ground covered. Slightly jargon-dense ('A2UI app', 'stateless parser service') and the long em-dash sentence packs several ideas that could be split.

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?

With no output schema, the description still tells the agent what a success returns (the compiled surface, rendered by MCP Apps hosts) and what a failure returns (a structured lint report), which is the key missing piece for a two-parameter tool. It leaves the payload shape to be inferred but supplies enough to act correctly.

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 in the schema, which sets the baseline at 3. The description adds real context by spelling out what the markdown must contain (frontmatter id/domain/name/source/license plus a # Steps section), which explains the otherwise opaque 'training-md contract' referenced by the domain enum.

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?

Names a specific verb and resource ('Compile a training.md / roadmap markdown document into a live interactive A2UI app') and immediately qualifies the mechanism ('DETERMINISTIC parser, no model involved'). It also distinguishes itself from the render/preview siblings by saying other hosts should pass the payload to preview_url.

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?

Gives concrete preconditions: the input must be MARKDOWN following the training-md contract, and lint errors must be fixed and the tool re-called. It also tells the agent what to do downstream on non-MCP-App hosts (hand off to preview_url). It stops short of explicit 'do not use this for X' exclusions, keeping it below a 5.

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

All A2UI Atomic Catalog 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.