Skip to main content
Glama

Check Invention

check_invention
Read-only

Check whether a complete invention document would load in a local Fyug, without playing it. Succeeds with {loadable, module_count, connection_count}; otherwise fails with the error a local load_invention reports. Pass json as a serialized JSON string of at most 64 KiB. Documents may define developments inline or refer to bundled content (see list_examples); this server reads no file or URL a document names and builds no output modules, and refuses such documents naming what they used.

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": {
      "json": "<json>"
    },
    "name": "check_invention"
  }
}

Input Schema

NameRequiredDescriptionDefault
jsonYesComplete invention JSON string (with modules, connections, etc.), at most 64 KiB.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond readOnlyHint=true, the description discloses the full result contract (loadable, module_count, connection_count on success; the same error a local load_invention reports on failure). It also discloses a real sandboxing limitation — no file or URL named by a document is read, no output modules are built, and such documents are refused — which is exactly the kind of behavior an agent cannot infer from the schema.

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?

Three sentences, front-loaded with the purpose and result shape, then the input form, then the restriction. Every sentence carries information, though the final clause ('builds no output modules, and refuses such documents naming what they used') is densely packed and takes a second read.

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?

There is no output schema, and the description compensates by naming the exact success payload fields and the failure mode. Combined with the 64 KiB limit and the bundled-content restriction, an agent has everything needed to call it and interpret the result.

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 coverage is 100% and the single parameter's description already states 'complete invention JSON string ... at most 64 KiB'. The description's 'Pass json as a serialized JSON string of at most 64 KiB' largely restates that, adding only the emphasis that it must be serialized rather than an object.

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?

States a specific verb and resource — validate whether an invention document would load — and pins the scope with 'without playing it', which separates it from play_preview. The success/failure contract is named immediately, so an agent knows exactly what the tool answers.

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 'without playing it' clause implicitly routes agents to play_preview when they want actual execution, and 'see list_examples' is given for resolving bundled content references. It stops short of an explicit 'do not use this to run a document' statement, but the context is clear.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources