Renforge Scene Tree

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

With no annotations, the description carries the full burden and does much of it: it names the returned fields, discloses that every reply carries an `omitted` completeness hint, lists the detail modes, and states the side effects of `save_as` (persists under `.renforge/scenes/`) and `diff_against`. It stops short of declaring read-only-ness or the cost/limits of the large payloads this can produce.

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?

Front-loaded with the core purpose and sibling contrast, then dense but high-yield sentences on scoping and options. Slightly long, but every clause maps to a real parameter or output behavior, so little is wasted.

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?

Given an output schema exists, return values needn't be spelled out, yet the description still enumerates key fields and the `omitted` hint. It covers most of a 13-parameter surface; the gap is the max_items/max_output_bytes/max_output_depth truncation controls, which matter for a tool whose output can be large.

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 0% across 13 params, so the description must compensate, and it does for most: it defines the `detail` enum values, the `layers`/`types`/`screen`/`ids` scoping role, the `include` composited colour/style/overflow options, `format="wireframe"`, `save_as`, and `diff_against`. The remaining params (project_path, max_items, max_output_bytes, max_output_depth) are left undocumented in both schema and description.

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+resource ('Perceive the whole scene as structured data') and immediately contrasts it with the sibling `renforge_list_ui_elements`, clarifying that this covers every layer displayable, focusable control and text block rather than focusables only. An agent can distinguish this from the other inspection tools without opening the 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 description explicitly routes the agent: use the sibling when only focusables matter, use this when the whole scene is needed, and it enumerates the scoping knobs (layers/types/screen/ids) and output shapes. It gives clear context but no explicit when-not or other alternatives (e.g., renforge_inspect_screen, renforge_hit_test).

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