Сцены Godot

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is carried by structured data. The description adds useful mode semantics but never warns that mode=create (with overwrite/root_type) mutates or destroys scene data, and its 'reading scenes' framing understates the destructive modes it does list. This is a mild inconsistency rather than a contradiction, since create is explicitly disclosed.

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?

It is compact and front-loaded: the reading purpose is stated first, then each mode is glossed in a single clause. No filler sentences. Slightly dense as one run-on line, but every clause earns its place.

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?

For a 16-parameter multi-mode tool with no output schema, the description cannot cover everything, but relative to its structure it is fairly complete: all five modes are named and their behaviors sketched. The remaining gap is parameter-level detail and any note on what create/backups return, but the mode enumeration covers the agent's primary routing decision.

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?

With 16 parameters and only 56% schema description coverage, the description should compensate more than it does. It maps several params implicitly to modes (path/source for tree, node for inspect, root_type for create, props for tree), but most of the under-documented params (limit, max_depth, max_nodes, overwrite, prop_limit, method_filter, property_mode) get no added meaning from the text.

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 states the resource (scenes/.tscn) and enumerates all five modes with a concrete verb-like gloss for each (state=exact file contents, tree=node tree, inspect=node properties/signals/methods, create=new scene, backups=backups). This lets an agent pick a mode without opening the schema. The only weakness is the headline 'Чтение сцены' (reading scenes), which undersells the write-capable 'create' mode bundled into the same tool.

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?

It provides implied usage per mode, notably that mode=state is 'the best way to understand what's actually written in the scene', which is genuine selection guidance among the read modes. However, it never states when to prefer this tool over the sibling godot_scene_edit (only referenced incidentally in the ops param description) and gives no explicit exclusions.

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