Инспекция и управление рантаймом

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that: it requires a live game to be started first and details how values are serialized for set, which an agent would otherwise have to discover by trial. It does not explicitly warn that get/set writes mutate running state, but the annotations carry that signal.

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 dense but front-loaded: the tool's purpose comes first, then mode semantics, then the startup prerequisite, then value formats. The mode and value-format sentences each earn their place, though the compact run-on enumeration of value encodings is heavy and would read better split up.

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?

With 25 parameters, 8 modes, and no output schema, the description covers mode semantics and value formats well but never describes what the read operations (tree/inspect/get) return, nor the undocumented parameters. For a high-complexity, mutation-capable tool with no output schema, this leaves gaps an agent must fill by guessing.

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?

Schema description coverage is only 44%, so the description must compensate. It explains the mode enum thoroughly and gives rich guidance on the value encoding (nested paths, "Vector2(10, 20)", {"$":"Vector2",...}, resource refs), which is the hardest parameter. However, roughly half the parameters (props vs property_mode, prop_names, prop_limit, method_filter, has_script, disconnect, items, args, from/to) get no explanation in the description, leaving meaningful ambiguity.

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 a specific verb+resource (inspecting and manipulating a live running game) and enumerates all eight modes with their meanings: tree, inspect, find, get/set, call, emit, connect. It clearly distinguishes the tool from siblings by deferring game startup to godot_run, so an agent knows this operates on an already-running game.

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 gives a concrete prerequisite ("Сначала запустите игру через godot_run { mode: 'start' }") and maps each mode to its use case, which is strong context. It stops short of stating when to prefer this over editor-time tools like godot_scene or godot_scene_edit, so there is no explicit exclusion guidance.

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