pick_region

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

With no annotations, the description carries the full burden and does well: it discloses that the overlay is semi-transparent, that the OS may refuse to raise the target app, and that Esc yields null. It omits blocking/timeout behavior and any permission requirements, which are the remaining gaps for an interactive screen-grab tool.

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 single most important fact (a user-driven overlay), followed by short indented notes on target format, return value, and the focus caveat. No filler sentences; each line carries distinct information.

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, yet the description still usefully clarifies the null-on-Esc semantics, and it covers the target format and the OS focus failure mode. Missing are the interactive/blocking contract and permission notes, but for a single-parameter tool this is close to sufficient.

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 0%, and the description fully compensates by enumerating the accepted forms for `target`: window title, process name, window_id, or `monitor:N`. It does not explain how to obtain a window_id (a sibling, list_targets, presumably supplies them), which keeps it short of a 5.

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?

First sentence names a specific action (drag-to-crop overlay) and makes the human-in-the-loop nature explicit: 'the USER selects the area.' That distinguishes it from automated siblings like start_recording or list_targets without naming them, so it is clear but not sibling-differentiated by name.

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 gives one real precondition ('tell the user to keep the app visible before calling this') and implies the interactive step precedes recording, but never states when to prefer this over starting a recording with no region, nor that list_targets should be used to resolve a window_id. Usage is implied rather than spelled out.

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