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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: only the latest screenshot is retained (retention policy), results are a slice rather than a full page, and screenshots only exist for browser fetchers — a real availability constraint. It stops short of describing the image format or the response when no screenshot exists.

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?

Three tight sentences, front-loaded with what the tool returns, then when to use it, then the paging/retention constraints. No redundant restatement of the title or schema.

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 (an image) and that it is a partial view requiring offset paging. The one remaining gap is what happens when no screenshot has been captured yet, though the 'only browser fetchers' note partially signals the failure mode.

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 67%, and the description supplies the missing context for the undocumented `which` enum by defining that 'error' means the last failed check. It also explains why `offset` exists ('full pages are long, so it's a slice: page down with offset'), reinforcing the schema's 'pixels from the top' note with the paging intent.

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 ('the latest screenshot of a monitor's page as an image') plus a variant ('its last failed check with which='error'), and immediately contrasts it with the text-based siblings ('for what the text can't show'). An agent can distinguish this from get_snapshot/get_diff without opening either schema.

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 selection criteria against the text tools — 'layout, images, a banner, a cookie wall, a block page' — and a precondition ('Only the browser fetchers take screenshots'). It implies rather than names the text alternative (get_snapshot), so the routing is clear but not fully explicit.

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