Skip to main content
Glama

artifact_design

Read-only

Generates a minimal fixture-shaped XML design for a specified Dynamics 365 Finance and Operations artifact type and name without reading or writing files.

Instructions

Generate a minimal fixture-shaped XML design without reading or writing files.

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": {
      "type": "<type>",
      "name": "<name>"
    },
    "name": "artifact_design"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
typeYes

Output Schema

NameRequiredDescriptionDefault
idNo
okYes
errorNo
contentNo
registryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.16.0

TDQS

C2.9/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true and openWorldHint=false, and the description usefully reinforces that by stating it neither reads nor writes files, which is meaningful added context for an artifact-producing tool. Beyond that it says nothing about whether the result is persisted, returned, or tied to some project fixture registry.

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?

One short sentence with no filler and the no-I/O constraint front-loaded where it matters. It is efficient, though the terseness edges into under-specification rather than economy, since nothing is left to anchor the meaning of "fixture-shaped".

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

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 explained, but for a tool with a 68-value enum and zero parameter documentation the description should say what the enum represents and what the generated design is for. It never clarifies where the XML goes or how it relates to artifact_build and artifact_validate, which is the main thing an agent needs.

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?

This is a judgment call: the description contributes nothing about `type` or `name`, and schema description coverage is 0%, so both parameters are fully undocumented in the schema while the enum holds 68 artifact kinds. That would normally be a serious gap. However, I decided the phrase "fixture-shaped XML design" does imply what the parameters are for: the `type` selects which artifact kind's XML shape to generate, and `name` identifies the fixture. That inference is legitimate but thin, so this stays at 4 rather than 5.

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

Purpose3/5

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

"Generate a minimal fixture-shaped XML design" gives a verb and an object, and the trailing clause clarifies it is a pure in-memory operation. However, "fixture-shaped XML design" is opaque jargon, and nothing distinguishes this from siblings like artifact_build or artifact_validate, so an agent cannot confidently pick it over them from the text alone.

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

Usage Guidelines2/5

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

There is no when-to-use guidance at all: no prerequisites, no indication of which sibling produces a similar result, and no statement of what a caller should do with the output. The only usable cue is the negative constraint that it touches no files, which is a side-effect note rather than routing guidance.

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