Scenes

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the mutating nature is already known; the description adds genuinely new behavior: 'Edits are auto-saved after every call', the 'becomes main scene if none is set' side effect of create, the save?=true default on close (closing persists), and the subtree-replacement semantics of pack_branch. This is real disclosure beyond the structured fields, though it never states what happens on failed saves or whether reload discards unsaved work.

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 summary is front-loaded and the per-action list is terse and scannable; every line adds information. The compressed pseudo-signature syntax ({path, root_type='Node2D', ...}) takes some parsing effort and slightly overloads the prose, keeping it off a perfect 5.

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 12-action, 11-parameter tool with no output schema, the description covers invocation well and annotates the one return type that matters most (source returns raw .tscn text). It leaves the return shapes of tree/current/list unspecified, but with no output schema and full schema coverage elsewhere, the definition is close to sufficient.

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 coverage is 100%, so a 3 would be the floor, but the description goes well past the schema by mapping which parameters apply to which of the 12 actions (e.g. create takes root_type/root_name/inherits/open/set_main; instance takes scene_path/parent/name/props). The schema itself provides no action-to-parameter mapping, so this is essential, non-redundant semantic value.

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 opening sentence names the verb family (create/open/save/inspect) and the exact resource (.tscn scene files), and crucially states the relational scope: 'The edited scene is the target of the node/signal tools.' An agent can immediately distinguish this from the node, signal, and project siblings without opening any schema.

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 action list implicitly routes between alternatives — 'list: every scene in the project' vs 'current: the edited scene and all open scenes' vs 'tree: node tree' are clearly differentiated. The note that other tools operate on the edited scene functions as cross-tool usage guidance. It stops short of explicit when-not-to-use or exclusion statements, so it lands just below a 5.

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