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

With no annotations provided, the description carries the full burden of disclosing side effects. It does so thoroughly: uniform scaling via a single factor (min(newW/oldW, newH/oldH)), preservation of proportions, recentring, propagation to layer positions/sizes/group pivots/keyframes, and letterboxing on aspect change. This level of behavioral detail is exceptional and beyond what any annotation block would typically provide.

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 description is long but every sentence carries distinct, high-value information: core action, scaling method, recentring, layer/keyframe consequences, sibling-page isolation, and common presets. The most operationally important detail ('ACTIVE page') is front-loaded. There is no filler or redundancy; the length is justified by the tool's genuine complexity.

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?

The description is fully self-contained for an agent to call correctly: it explains what happens to the canvas, layers, keyframes, sibling pages, and even gives the select_page workflow. Since no output schema is present, the description appropriately focuses on invocation and side effects rather than return values. Nothing an agent needs to know to use this tool safely is missing.

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% and all parameter descriptions are already clear. The description adds value by linking width/height to real-world presets (1080×1920 for Reels/TikTok/Shorts, etc.) and by clarifying that width/height refer to the resulting canvas after uniform scaling. The 'ACTIVE page' context is also critical for projectId semantics, even though the schema independently says projectId selects the existing project.

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 opens with a clear verb-resource pair: 'Resize the ACTIVE page's canvas to width × height pixels.' It distinguishes itself from siblings by emphasizing 'ACTIVE page' and by focusing specifically on canvas resizing, none of the sibling set_* tools cover this exact operation. The scope and expected effect are unambiguous.

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 explains the per-page ownership: 'Each page owns its size, so this leaves sibling pages untouched — select_page then set_canvas_size again to resize another one.' This tells the agent not only when to use the tool but the exact prerequisite workflow for applying it to multiple pages. It also provides common size presets mapped to platforms, which gives practical usage context.

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