mcp-vdd

Implement Task

vdd_implement

Destructive

Executes a single development task end-to-end: load constitution and specs, implement code, verify results, and commit with an impact-chain message. Provide a task ID to apply this full workflow.

Instructions

VDD Phase 7b: Execute one task — load constitution, spec, plan, and contracts, implement, verify, and commit with an impact-chain commit message. Mutates source code and commits to git. Pass taskId (e.g. "TASK-003") from the task returned by vdd_get_next_task. Run one task at a time, after vdd_get_next_task; for read-only inspection of tasks use vdd_get_next_task or vdd_trace instead.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`taskId`	Yes	Task ID to implement (e.g., "TASK-003")
`projectRoot`	No	Project root: directory that constitution.md and the vdd/ folder are written to and resolved against (default ".")	.

Output Schema

TableJSON Schema

Name	Required	Description
`_sdt`	Yes	Strategy-and-Tactic instructions for the next step
`error`	No	Error message when the phase fails
`_phase`	Yes	VDD phase that produced this result
`output`	No	Additional structured phase output
`success`	Yes	Whether the phase completed successfully
`artifact`	No	Primary artifact produced or returned
`gateResult`	No	Quality-gate result, when the phase runs a gate

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.3Sep 24, 2026

changedInput schema / properties / projectRoot / description

Previous value: -"Path to project root directory"New value: +"Project root: directory that constitution.md and the vdd/ folder are written to and resolved against (default \".\")"

Changed1 schema field changedv0.1.2Sep 24, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "_phase": {
+      "description": "VDD phase that produced this result",
+      "type": "string"
+    },
+    "_sdt": {
+      "description": "Strategy-and-Tactic instructions for the next step",
+      "type": "string"
+    },
+    "artifact": {
+      "description": "Primary artifact produced or returned",
+      "type": "string"
+    },
+    "error": {
+      "description": "Error message when the phase fails",
+      "type": "string"
+    },
+    "gateResult": {
+      "additionalProperties": false,
+      "description": "Quality-gate result, when the phase runs a gate",
+      "properties": {
+        "checks": {
+          "description": "Number of checks run",
+          "type": "number"
+        },
+        "passed": {
+          "description": "Whether the quality gate passed",
+          "type": "boolean"
+        },
+        "total": {
+          "description": "Total number of checks",
+          "type": "number"
+        }
+      },
+      "required": [
+        "passed",
+        "checks",
+        "total"
+      ],
+      "type": "object"
+    },
+    "output": {
+      "additionalProperties": {},
+      "description": "Additional structured phase output",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "success": {
+      "description": "Whether the phase completed successfully",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "success",
+    "_phase",
+    "_sdt"
+  ],
+  "type": "object"
+}

First observedv0.1.0Sep 24, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, and the description adds meaningful specifics: it mutates source code, commits to git, loads constitution/spec/plan/contracts, and uses an impact-chain commit message. This goes beyond the generic destructive flag, though it stops short of describing reversibility or failure behavior.

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?

The description is dense but every sentence earns its place: what happens, what is mutated, what input to provide, and when to use it. The phase label 'VDD Phase 7b' is mildly jargon-heavy, but the rest is concrete and front-loaded.

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

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive mutation tool with an output schema, a documented destructive annotation, and full parameter coverage, the description gives sufficient procedural context: load inputs, implement, verify, commit, and the prerequisite call. An agent has what it needs to invoke this correctly.

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?

Schema coverage is 100%, so the schema carries most parameter meaning. The description adds valuable context for taskId by specifying it comes from the task returned by vdd_get_next_task and showing a concrete example. projectRoot is already well documented in 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?

The description states a specific verb (Execute), a specific resource (one task), and the precise phase (VDD Phase 7b). It also differentiates itself from read-only siblings by explicitly directing inspection tasks to vdd_get_next_task or vdd_trace.

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

Usage Guidelines5/5

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

Usage is explicit: run one task at a time, after vdd_get_next_task, and pass the taskId returned from it. It also names alternatives for read-only inspection, which tells an agent when not to call this tool.

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

Deploy Server