PCFHub

Validate a pcfhub.json

validate_manifest

Read-onlyIdempotent

Check a pcfhub.json against the rules PCFHub applies when it publishes a control: the schema version, the control block (namespace, constructor, type and framework), the demo's fidelity, bundle and presets, the media files it declares, and the release artifacts it expects to find. Use it while writing or reviewing that file, before a release is tagged. An invalid manifest is an ordinary result — valid false, with errors that block publishing and warnings that do not, each carrying the JSON pointer it applies to — so read the result rather than retrying. Only an empty, unreadable or oversized manifest (over 64 KB) is an error.

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": {
      "manifest": "<manifest>"
    },
    "name": "validate_manifest"
  }
}

Input Schema

Name	Required	Description	Default
`manifest`	Yes	The full contents of pcfhub.json, as JSON text.

Output Schema

Name	Required	Description
`valid`	Yes	False when there is at least one error. Warnings alone leave it true.
`errors`	Yes	Must be fixed; publishing refuses the manifest until they are.
`warnings`	Yes	Do not block publishing, but reach the author through their own CI.
`schemaVersion`	Yes	The manifest schema version it was checked against.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 26, 2026
- changedOutput schema / properties / schemaVersion / type
```
Previous value: -"string"New value: +"integer"
```

Changed1 schema field changedSep 16, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "errors": {
+      "description": "Must be fixed; publishing refuses the manifest until they are.",
+      "items": {
+        "properties": {
+          "message": {
+            "type": "string"
+          },
+          "pointer": {
+            "description": "RFC 6901 JSON pointer to the part of the manifest at fault, e.g. \"/demo/presets/0\".",
+            "type": "string"
+          }
+        },
+        "required": [
+          "pointer",
+          "message"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "schemaVersion": {
+      "description": "The manifest schema version it was checked against.",
+      "type": "string"
+    },
+    "valid": {
+      "description": "False when there is at least one error. Warnings alone leave it true.",
+      "type": "boolean"
+    },
+    "warnings": {
+      "description": "Do not block publishing, but reach the author through their own CI.",
+      "items": {
+        "properties": {
+          "message": {
+            "type": "string"
+          },
+          "pointer": {
+            "description": "RFC 6901 JSON pointer to the part of the manifest at fault, e.g. \"/demo/presets/0\".",
+            "type": "string"
+          }
+        },
+        "required": [
+          "pointer",
+          "message"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "valid",
+    "schemaVersion",
+    "errors",
+    "warnings"
+  ],
+  "type": "object"
+}

First observedSep 13, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already cover readOnly and idempotent hints, so the description doesn't need to repeat them. It adds substantial behavioral context: that an invalid manifest is an ordinary result (valid false), errors block publishing while warnings do not, each carries a JSON pointer, and only empty, unreadable, or oversized (>64 KB) manifests are errors. This goes beyond annotations and is critical for correct invocation.

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 two sentences: the first front-loads the purpose and scope, the second covers usage, result semantics, and error conditions. There is no redundancy, and every clause adds value. It is efficient and well-structured.

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?

The tool is complex (validates many aspects), but the description enumerates all validation areas and explains the result behavior clearly. Since an output schema exists, it doesn't need to detail the return structure; it covers everything an agent needs to invoke it correctly, including edge cases (oversized manifest).

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?

The schema already provides 100% coverage for the single parameter 'manifest' (full contents as JSON text), so the baseline is 3. The description adds an important constraint not in the schema: manifests over 64 KB are treated as errors, which helps the agent set expectations for valid input. This extra information raises the score to 4.

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 uses a specific verb ('check') and clearly identifies the resource (pcfhub.json) and the rules it validates against, listing the exact aspects (schema version, control block, demo fidelity, bundle, presets, media files, release artifacts). It is unmistakably a validation tool, distinct from the sibling retrieval/query tools.

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?

It explicitly states when to use the tool: 'Use it while writing or reviewing that file, before a release is tagged.' It also advises to read the result rather than retry, which is a practical usage hint. It does not name alternatives, but the sibling set (get, list, search) makes the distinction clear, so the guidance is sufficient.

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

All PCFHub tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?