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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds genuinely new behavioral facts: the capture asks the live authenticated page rather than a synthetic renderer, incurs no billing, requires a visible open Canvas, and returns ImageContent plus layout/loading metadata. These are prerequisites and side-effect disclosures an agent would otherwise have to discover by failing.

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 use-case and the live-PNG distinction are front-loaded, then parameters, then returns, then prerequisites and alternatives. Every clause carries information, though the middle parameter sentence is a dense run-on that packs five enum values into one line.

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 correctly states the return type (ImageContent PNG plus layout/loading metadata), and it covers prerequisites and routing. But for a 9-parameter tool with zero schema descriptions, several parameters (max_edge_px sizing, expected_rev concurrency guard, instance_id) remain undefined anywhere, leaving real invocation ambiguity.

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%, so the description has to carry parameter meaning. It usefully explains the target enum ('viewport uses its current camera, fit shows the entire graph; rect/point/nodes focus a region') but says nothing about max_edge_px, expected_rev, instance_id, or the x/y versus rect relationship. Partial compensation only.

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 ('screenshot of an OPEN Canvas exactly as the user sees it, including graph, node thumbnails, viewport and live UI') and contrasts with a synthetic renderer. It is clearly distinguishable from siblings like aimixer_canvas_preview and aimixer_canvas_inspect_images, which the description names.

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 explicit when-to-use ('OPEN Canvas exactly as the user sees it'), a hard prerequisite ('Requires an open visible Canvas page'), and two named fallbacks with conditions: aimixer_canvas_view_session when the page is unavailable, aimixer_canvas_inspect_images for individual images. Routing is unambiguous.

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