Wavedash

Plan Wavedash Implementation

wavedash_implementation_planner

Read-only

Plan and guide a Wavedash browser game integration from the user's goal, engine, and requested features. Call this first for any request to build, deploy, upload, or release a game on Wavedash, or to add Wavedash SDK features. Choose the stage: plan (architecture and reading order), setup (CLI install, sign-in, SDK init, wavedash.toml, local testing), features (SDK reference for the requested features), or deploy (upload and release checklist). Returns ordered steps, boundaries, and the relevant docs.wavedash.com pages with content. Read-only and unauthenticated.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`goal`	Yes	What the user wants to build, deploy, or integrate, including the game type and the Wavedash outcome.
`stage`	No	plan: architecture and reading order. setup: CLI, SDK init, config, local testing. features: SDK reference for the requested features. deploy: upload and release checklist.	plan
`engine`	No	Optional engine or framework as the user names it, for example Phaser, Unity WebGL, Godot 4, three.js, React, Rust, or custom.
`features`	No	Optional requested Wavedash features, for example multiplayer, leaderboards, achievements, cloud saves, ugc, players, paid content.

Output Schema

TableJSON Schema

Name	Required	Description
`docs`	Yes	Docs pages to read for this stage.
`goal`	Yes
`text`	Yes	Human-readable plan.
`stage`	Yes
`steps`	Yes	Ordered implementation steps for this stage.
`engine`	Yes
`features`	Yes
`boundaries`	Yes	What this MCP and Wavedash do not do.
`next_tools`	Yes	Recommended follow-up tool calls.

Schema Changelog

Changes observed during successful MCP inspections.

Changed14 schema fields changedSep 22, 2026

changedInput schema / properties / engine / description

Previous value: -"Optional engine/framework, for example phaser, unity, godot, three.js, react, rust, or custom."New value: +"Optional engine or framework as the user names it, for example Phaser, Unity WebGL, Godot 4, three.js, React, Rust, or custom."

changedInput schema / properties / features / description

Previous value: -"Optional requested Wavedash features, for example multiplayer, achievements, leaderboards, cloud-saves, ugc, players, paid-content, upload, or publishing."New value: +"Optional requested Wavedash features, for example multiplayer, leaderboards, achievements, cloud saves, ugc, players, paid content."

changedInput schema / properties / goal / description

Previous value: -"What the user wants to build or integrate, including the game type and Wavedash-related outcome."New value: +"What the user wants to build, deploy, or integrate, including the game type and the Wavedash outcome."

addedInput schema / properties / stage

Added value: +{
+  "default": "plan",
+  "description": "plan: architecture and reading order. setup: CLI, SDK init, config, local testing. features: SDK reference for the requested features. deploy: upload and release checklist.",
+  "enum": [
+    "plan",
+    "setup",
+    "features",
+    "deploy"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / boundaries

Added value: +{
+  "description": "What this MCP and Wavedash do not do.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / docs

Added value: +{
+  "description": "Docs pages to read for this stage.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "slug": {
+        "description": "Docs path, for example sdk/setup.",
+        "type": "string"
+      },
+      "url": {
+        "description": "Full docs.wavedash.com URL.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "slug",
+      "url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / engine

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

addedOutput schema / properties / features

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / goal
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / next_tools

Added value: +{
+  "description": "Recommended follow-up tool calls.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / stage

Added value: +{
+  "enum": [
+    "plan",
+    "setup",
+    "features",
+    "deploy"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / steps

Added value: +{
+  "description": "Ordered implementation steps for this stage.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / properties / text / description

Previous value: -"Human-readable tool result text."New value: +"Human-readable plan."

changedOutput schema / required

Previous value: -[
-  "text"
-]New value: +[
+  "text",
+  "stage",
+  "goal",
+  "engine",
+  "features",
+  "steps",
+  "docs",
+  "boundaries",
+  "next_tools"
+]

AddedJun 30, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint, and the description aligns with those. The description adds valuable behavioral context beyond annotations by stating 'Read-only and unauthenticated' and by disclosing what it returns: 'ordered steps, boundaries, and the relevant docs.wavedash.com pages with content.' No contradiction exists.

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 front-loaded with the core purposehol; every sentence contributes. The stage breakdown is dense but necessary for this multi-mode tool, and there is no filler or repetition. It is long enough to be useful and short enough to scan.

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?

Given the tool's complexity, the rich input schema, and the presence of an output schema, the description covers the essential context: when to call it, the stage choices, what it returns, and its read-only/unauthenticated behavior. An agent has enough information to select and invoke this tool correctly without additional documentation.

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 baseline is 3, but the description adds meaning beyond the schema by expanding each stage with concrete contents, e.g., setup includes 'CLI install, sign-in, SDK init, wavedash.toml, local testing.' It also gives representative examples for engine and features, helping an agent map user language to parameters.

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 opens with a specific verb and resource: 'Plan and guide a Wavedash browser game integration.' It also defines the scope across goal, engine, and requested features. It clearly differentiates this planning tool from the sibling docs tools by instructing agents to call it first for build/deploy/upload/SDK-feature requests.

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 gives an explicit trigger: 'Call this first for any request to build, deploy, upload, or release a game on Wavedash, or to add Wavedash SDK features.' This is strong usage guidance, but it does not explicitly name alternatives or state when to prefer get_wavedash_doc, search_wavedash_docs, or validate_wavedash_config, so it stops short of a full 5.

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

All Wavedash 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.