editor_scene_graph

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

Annotations only declare readOnlyHint=true; the description adds real value beyond that by disclosing that the result includes unsaved runtime state and by quantifying the truncation behavior (500 nodes or 32 levels) with the meaning of the truncated flag. It does not discuss payload size, cost, or whether truncation loses whole subtrees versus leaf nodes, which keeps it off a 5.

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?

Two sentences, zero waste. Scope and the 'live/unsaved' qualifier come first, and the truncation caveat follows as a compact second sentence.

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 an output schema present, return-value shape needn't be restated, and the one non-obvious output trait (truncation) is explained. No parameters, read-only annotation, and the live-vs-saved distinction are all covered, so an agent has enough to call it correctly.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param schema applies. The description correctly avoids inventing parameter talk and instead spends its words on output behavior.

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?

States a specific verb and resource: 'Returns the live actor tree from every scene loaded in the Flax Editor.' The 'every scene / including unsaved runtime state' scoping distinguishes it in substance from per-scene tools, but it never names the near-siblings (scene_outline, scene_list, editor_find_actors), so the agent must infer the boundary.

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?

There is no explicit 'use this when' or 'do not use for' statement. The phrase 'every scene loaded... including unsaved runtime state' implies the case where a whole-project live snapshot is wanted rather than a single-scene or single-actor lookup, but routing between this and scene_outline/editor_find_actors is left to inference.

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