omni_manage

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

With no annotations, the description carries the burden. It explicitly states 'Execute arbitrary GDScript in the Editor process with full permissions' and 'Call ANY method on ANY Godot Object', which discloses its high-impact nature. It also mentions writing properties and instantiating prefabs. However, it doesn't discuss potential side effects, reversibility, or the need for caution, so transparency is partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with a one-line summary, a bullet list of ops with code-like signatures, and a final note on call shape. Every line adds necessary detail for the many operations. It could be slightly trimmed, but the structure is logical and front-loaded with the key point. The length is justified by the tool's breadth.

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

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

The description covers all ops and their parameters, and explains the canonical call shape with op and params. It does not describe return values or error handling, but an output schema is indicated (though not shown), which might cover that. It also doesn't explain the session_id parameter, which is present in the schema. Overall, it's quite complete for such a multifaceted tool, with minor omissions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage and params is free-form (additionalProperties: true), so the description is the only source of parameter meaning. It fully compensates by listing each op with its parameter names, defaults, and some type hints (e.g., eval(code, mode='auto', inputs={}), mesh_primitive(primitive_type='box', ...)). This is essential for correct invocation and is exceptionally detailed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a broad purpose: 'Universal Godot engine control, reflection, script evaluation, and editor UI automation.' It lists specific ops with verbs like eval, call, get, set, etc., making it evident what the tool does. However, it doesn't explicitly differentiate from the many sibling tools (e.g., node_manage, shader_manage), instead positioning itself as a catch-all, which is clear enough but not targeted.

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

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

The description provides no guidance on when to use this tool versus its siblings. It lists capabilities but doesn't state conditions like 'use this for generic reflection, use node_manage for node-specific operations' or mention exclusions. The canonical call shape is explained, but not the selection criteria. This leaves the agent to infer usage from the broad 'universal' claim.

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