Specky

Write Design Document

sdd_write_design

Generates a DESIGN.md file containing architecture overview, Mermaid diagrams, ADRs, and API contracts from structured inputs.

Instructions

Generates and writes DESIGN.md with architecture overview, Mermaid diagrams, ADRs, and API contracts.

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": {
      "architecture_overview": "<architecture_overview>",
      "mermaid_diagrams": "<mermaid_diagrams>"
    },
    "name": "sdd_write_design"
  }
}

Input Schema

Name	Required	Description	Default
`adrs`	No	Architecture Decision Records
`force`	No	Overwrite existing files if true
`spec_dir`	No	Spec directory path (relative to workspace root)	.specs
`data_models`	No	Data model: entities, relationships, and storage strategy
`api_contracts`	No	API contracts
`cross_cutting`	No	Cross-cutting concerns: logging, monitoring, caching, configuration
`error_handling`	No	Error handling: detection, logging, propagation, and recovery
`feature_number`	No	Feature number (zero-padded, e.g. '001')	001
`infrastructure`	No	Infrastructure: deployment, scaling, monitoring, and operations
`system_context`	No	System context: who uses the system and what external systems it integrates with (C4 Level 1)
`component_design`	No	Component design: internal modules/services and responsibilities (C4 Level 3)
`mermaid_diagrams`	Yes	Mermaid diagrams
`code_level_design`	No	Code-level design: key classes, interfaces, and patterns (C4 Level 4)
`architecture_overview`	Yes	High-level architecture description
`security_architecture`	No	Security: authentication, authorization, encryption, and threat model
`container_architecture`	No	Container architecture: deployable units and communication patterns (C4 Level 2)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.4.0-rc.14May 3, 2026

TDQS

B3.2/5.0

Behavior2/5

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

Annotations provide no safety info (readOnlyHint false, no destructiveHint). Description mentions writing a file, but does not disclose overwrite behavior (though force param exists), naming conventions, or side effects (e.g., file creation in .specs dir). For a write operation, more behavioral context is needed beyond 'generates and writes.' No contradiction with annotations.

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?

Single sentence, no fluff. Lists key output contents. Appropriate length given complexity. Front-loaded with purpose.

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?

With 16 parameters (2 required), no output schema, and no additional context, the description is too brief. It lacks explanation of default directory (.specs), feature_number naming, and how optional parameters combine. Agents need more context to invoke correctly, especially for a design document generation tool.

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 has 100% coverage, with each parameter described. Description adds no extra meaning beyond that. Baseline 3 is appropriate as schema does the work, and description does not enhance parameter understanding.

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?

Description clearly states the tool generates and writes DESIGN.md with specific content (architecture overview, Mermaid diagrams, ADRs, API contracts). Verb 'writes' is specific, and resource 'DESIGN.md' is explicit. This distinguishes it from siblings like sdd_write_spec (which likely writes spec docs) and sdd_generate_docs (which may generate multiple docs).

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?

No guidance on when to use this tool vs alternatives (e.g., sdd_write_spec, sdd_implement). No prerequisites mentioned, no conditions for use. Agents must infer usage from context. Lack of when-not-to-use or alternative references limits effective selection.

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

Deploy Server