Paint: look at the canvas

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and 'without changing anything' is consistent with them. The description adds the layer-only viewing tip but says nothing about what the return payload looks like (image data vs URL, size limits, cost of full previews), which is the main behavioral unknown for a preview tool.

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 short sentences, front-loaded with the read-only guarantee, then the usage scenarios, then the one option worth calling out. No 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?

For a 5-parameter tool with a nested region object and no output schema, the description is minimal: it never explains what the returned 'picture' actually is, and the auto/thumb/full preview enum is left undocumented in both description and schema. Annotations cover the safety profile, but the return-shape gap keeps this at minimum-viable.

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 80%, so the schema already documents layer, canvas, region and preview_size. The description's 'Set layer:true' restates the schema's own layer description and adds no new syntax or format detail for preview/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?

States a specific verb and resource ('Return the current picture') plus the key invariant ('without changing anything'), which clearly separates it from mutating siblings like paint_line or paint_clear. It does not, however, contrast with the potentially overlapping paint_inspect or paint_export, so sibling routing is only partly resolved.

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?

Gives concrete use cases — checking work, comparing against a reference, re-reading after a long session — so an agent knows when to reach for it. There is no explicit when-not guidance or named alternative (e.g. for reads that should not return an image), so it falls short of a 5.

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