Observe a MAX+plus II window

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds the observation lifecycle note ('each input consumes its observation') and a diagnostics caveat, but the latter references a 'diagnostics' concept absent from the schema, so the added signal is thin.

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 sentences, front-loaded with the return payload, then the pre-action guidance, then a caveat. Tight and mostly waste-free, though the trailing diagnostics sentence is vague and slightly muddies the close.

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 carries the return-value burden and lists the key outputs, plus the pagination model lives in the schema. It is complete enough to call correctly, though the one-shot observation semantics could be stated more explicitly.

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 100%, so the eight parameters (windowId provenance, pagination offsets, includeText/includeScreenshot) are already documented in the schema, including the 'never invent one' warning. The description adds no parameter meaning beyond that, making the baseline 3 correct.

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 (observe/return) and resource (a MAX+plus II window) and enumerates the returned artifacts: native screenshot, UI Automation tree, focus, window bounds, and observationId. This lets an agent know exactly what it gets. It does not, however, distinguish itself from the adjacent desktop_status / desktop_windows siblings.

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?

'Inspect before acting' implies the tool is a read step preceding desktop_action, which is useful guidance. But it names no alternatives, no explicit when-not conditions, and does not clarify how it differs from desktop_windows or desktop_status, leaving the agent to infer routing.

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