screenshot

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior ('unoccluded' capture, compositor fallback when no app is passed) but says nothing about what is returned (image data vs. path) or how failures are surfaced.

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, front-loaded sentences with no filler; the primary capability leads and the scoping caveat follows. Slightly terse at the cost of completeness, and 'low-level target' is vague jargon.

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 11 parameters, a nested region object, three enums, no required params and no output schema, the description is thin. It omits return-value expectations and the interaction between region, coordinate_space and the app/window selection, leaving the agent to guess on most of the surface.

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 only 27% across 11 parameters, so the description must compensate but does not. Only the app/target precedence is clarified; zoom, scale, region, format, quality, max_dimension, show_cursor and cursor_source are undocumented in both description and schema.

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 ('Capture ... screenshot') plus the scope rule (app/window, else the visible compositor). However, it gives no differentiation from the near-identically-named sibling get_screenshot, which an agent could easily confuse with this tool.

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?

'Prefer app over low-level target' gives one concrete selection rule between two of its own parameters, and the fallback to the compositor when no app is passed is implied. There is no guidance on when to choose this tool over get_screenshot or ocr, so routing among siblings is left to inference.

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