Skip to main content
Glama
agtmwebtoon

autocad-mcp

by agtmwebtoon

validate

Read-only

Validates design intents by generating and pruning branch candidates against constraint trees, returning deterministic command sequences for AutoCAD execution.

Instructions

LLM 모호성 → Branch 후보 생성 → Constraint Tree prune → Deterministic 실행 순서 반환.

Operations: branch — DesignIntent → Branch 후보 생성. data: {intent: {shape_type, params, features?}} check — Branch 후보들 → Constraint Tree 검증 (valid/pruned 분류). data: {branches: [...]} select — Valid Branch 중 best 선택 (min cost + semantic priority + hash). data: {valid_branches: [...]} pipeline — Intent 리스트 → branch/check/select 전 단계 한번에. data: {intents: [{shape_type, params, features?}, ...]}

pipeline 반환 예시 (PASS): {ok: true, selected_branch: {branch_hash, total_cost, commands: [...]}, stats: {...}}

pipeline 반환 예시 (FAIL — 모두 prune): {ok: false, all_pruned: true, failures: [{branch_hash, failed_node, reason, suggestion}]}

selected_branch.commands 를 순서대로 entity/layer/... 툴에 실행하면 항상 동일한 input → 동일한 output 이 보장된다.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
rule_setNodefault
operationYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description adds valuable behavioral context: the tool is deterministic ('항상 동일한 input → 동일한 output 보장'), it prunes branches ('valid/pruned 분류'), and it can return all_pruned failures with suggestions. It does not contradict the read-only annotation and goes beyond it by describing the output structure's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear overview, an operations list with data formats, and concrete return examples for pipeline (PASS/FAIL). Each sentence contributes information without redundancy, and the format is scannable and front-loaded with the core workflow.

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?

The description is quite complete for a complex tool with an output schema: it covers the high-level pipeline, lists all operations, provides data shapes, and gives return examples for the pipeline both on success and failure. However, it omits details about the 'rule_set' parameter and does not show return formats for the individual branch/check/select operations, which keeps it from being fully complete.

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%, so the description must compensate. It defines the data structures for each operation (e.g., branch data: {intent: {shape_type, params, features?}}), which helps clarify the 'data' parameter. However, the 'rule_set' parameter is not explained at all, and the 'operation' parameter's allowed values are only implied by the operations list, leaving a significant gap.

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?

The description clearly explains the tool's core workflow: it takes LLM ambiguity, generates branch candidates, prunes them via a constraint tree, and returns a deterministic execution order. The operations list (branch, check, select, pipeline) specifies exact actions, and the final line distinguishes it from sibling tools by directing execution of returned commands to entity/layer/etc.

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 description implies when to use the tool: 'selected_branch.commands 를 순서대로 entity/layer/... 툴에 실행하면' indicates this is a precursor to executing on other tools. However, it does not explicitly state when not to use it or compare it to alternatives besides the implicit contrast with the sibling creation/modification tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/agtmwebtoon/autocad-validation-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server