canvas_snapshot

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

With zero annotations the description carries the full burden, and it does disclose real behavior: the frame option temporarily switches animation frame and restores the current one (a side effect worth knowing), layer blanking makes everything else transparent, grid burns labelled coordinate lines into the returned image, and max_size caps the longest side. What is missing is the return channel (image content vs. path) and whether output is cached or re-rendered per call.

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 core purpose is front-loaded in the first clause, then each optional behavior gets exactly one compact clause. No filler, no repetition of the schema, and the parenthetical layout makes scanning for the parameter of interest trivial.

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 an 8-parameter, zero-annotation, no-output-schema tool this is close to self-sufficient: all options are explained and the frame-restore side effect is called out. Minor omissions remain – the layer value format and the response format – but neither would likely cause a failed call.

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%, so the description must do all the work, and it covers nearly every parameter: x/y/width/height are in canvas pixels, max_size caps the longest side with a stated 64-4096 range, and grid/layer/frame each get a one-line meaning. The gap is the layer parameter, whose accepted value form (name vs. id/index) is never specified, and no hint that x/y/width/height must be supplied together as a region.

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?

"Return the current composite image so you can SEE the canvas" names a concrete verb (return) and resource (composite canvas image), and the follow-on options (zoom, layer isolation, grid overlay, frame) describe capabilities that clearly are not those of siblings like view_image or export_image. It stops short of explicitly naming which sibling it replaces, so the differentiation is inferred from capabilities rather than stated.

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?

Usage is implied through purpose clauses – "so you can SEE the canvas", "to read off exact positions" – which tell the agent the intended scenarios for grid and zoom. However, no alternative is named: an agent choosing between canvas_snapshot, view_image, read_pixels, and analyze_image gets no explicit when-to-pick-this guidance, and no exclusions are given.

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