system_capture_screen

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

Annotations already cover the safety profile (idempotentHint true, destructiveHint false), so the bar is lower. The description adds genuinely useful context beyond them: the Screen Recording permission requirement and the authorized-file-root confinement for the output. It omits the human-approval requirement implied by _approvalId and the non-overwrite behavior, but the core behavioral traits are disclosed.

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 sentences, front-loaded with the action and scope, with the permission requirement immediately following. Nothing redundant; the version tag is compact metadata.

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?

An output schema exists, so return values need no explanation, and the description carries the permission and file-root constraints. Approval workflow and overwrite behavior live in the schema, so the description is complete enough for correct invocation. Marginal room to note the approval gate.

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 75%, below the 80% baseline, and windowId ships with an empty description. The phrase "full display or one window" compensates for exactly that gap by explaining windowId's semantics (its presence selects single-window mode) and its optionality. The remaining three parameters are documented in the 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?

"Capture full display or one window to PNG inside an authorized file root" gives a specific verb (capture), a clear resource (full display or one window), the output format (PNG), and a scope constraint (authorized file root). An agent can tell this apart from window-inspection siblings like system_get_active_window or system_list_windows. It stops short of the explicit 5 because it never names those siblings directly.

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?

It states a prerequisite ("Screen Recording permission required") and implies the display-vs-window choice, but gives no when-to-use/when-not guidance relative to alternatives and no exclusions. Usage context is only implied.

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