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

Annotations already cover safety (readOnlyHint, idempotentHint, non-destructive), and the description reinforces this with 'Read-only: never changes the saved project.' It adds genuinely useful context beyond annotations — no rendering occurs, bounds are approximate, and legacy renderer arguments return 'renderer_retired' rather than fake DOM/screenshot data — but it does not describe return shape details or export limits/costs. With annotations carrying the safety profile, a 3 is appropriate for the incremental value added.

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 trigger and the scope constraint are front-loaded in the first two sentences, and the alternative-tool guidance follows. The result is fairly dense and slightly run-on but no sentence is pure filler.

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 no output schema, the description does the work of explaining returns (frame rectangle, contained cards with approximate bounds, overlapping pairs, overflow cards, minimum gaps). What remains thin is parameter-level guidance for expected_rev, min_zoom, and the exact identity of the legacy arguments.

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 0% with 7 parameters and no per-parameter descriptions in the schema, so the description bears full responsibility. It only hints that frame_ids selects frames and vaguely gestures at 'legacy renderer-only arguments' (likely viewport_width/height, min_zoom, screenshot_frame_id) without naming which parameters those are, and says nothing about expected_rev or min_zoom semantics. Substantial compensation is missing.

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 ('positions and collisions of frames/scenes') plus the computation basis ('from saved graph coordinates, no rendering'). The return payload is enumerated (frame rectangle, cards inside, overlapping pairs, sticking-out cards, minimum gaps), which lets an agent tell it apart from rendering/view tools.

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?

Opens with an explicit trigger ('Use when you need positions and collisions of frames/scenes') and names the alternative for the real UI case ('aimixer_canvas_view_session' or widget app tools). It also declares a negative condition — sizes are editor defaults, not measured pixels — which keeps the agent from misusing it for pixel-accurate checks.

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