Did the screen change?

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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real value beyond them: the checksum comparison model, the three possible answer states, and the cost motivation for polling. It does not say what happens with an invalid or stale checksum, or how a region outside the screen bounds is treated, which is the remaining gap.

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?

Front-loaded with the core purpose, then the protocol, then the alternative — a good ordering. The prose is dense and reads as a semicolon-chained run-on, but no sentence is 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?

With no output schema, the description carries the burden of return values and does so by naming the three answer states. For a three-parameter polling tool with full annotation coverage, this is nearly complete; only error/stale-checksum behavior is unaddressed.

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 the nested region object is self-describing, so baseline is 3; the description earns an extra point by explaining the temporal coupling between 'since' and a prior call's checksum, which the schema alone cannot convey. It adds no detail on how 'window' matches titles beyond the schema's 'part of its title'.

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 plus resource ('tell whether the screen, a window or a rectangle has changed') and immediately differentiates itself from amiga_screenshot by noting no picture is sent. The checksum mechanism makes the tool's identity unambiguous against siblings like amiga_wait.

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 the exact call protocol: first call without 'since' returns 'first look' plus a checksum, later calls pass that checksum as 'since'. It also names the alternative for the blocking case ('to block until a change use amiga_wait with what=change') and the condition choosing it ('cheap polling when a screenshot would be too big').

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