capture_screen

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

Annotations only cover the safety profile (readOnly/idempotent/non-destructive); the description adds substantial context beyond them: required OS permissions, that absence yields a blank capture with a self-explaining error, Linux backend dependencies, that a PNG is written to the temp folder, and what is returned (path, size, preview). This is unusually rich behavioral disclosure.

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 purpose and alternatives, then prerequisites and returns; most sentences earn their place. The trailing chaining advice ('locate elements with locate or grid + zoom and annotate with scale 1') is useful but slightly dense and less crisp than the rest.

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?

No output schema exists, yet the description still states the return surface (path, size, preview) as well as prerequisites and failure behavior, so an agent knows how to call it, what to expect back, and what to do next. Nothing material is missing.

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% and the single 'region' parameter is fully documented in the schema (formats, defaults, whole-display omission). The description only restates the whole-screen/one-region scope without adding format or coordinate semantics, so the baseline 3 applies.

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 ('Screenshot the whole screen or one region') with scope ('as the user sees it right now'), and names the siblings it differs from (capture_window, capture_web) with the distinguishing condition (overlap from other windows / exact element rects). An agent can select it without opening any other schema.

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 an explicit positive trigger ('spans several windows or is not in any one window') and two explicit alternatives with the condition selecting each ('prefer capture_window for one app', 'capture_web for web pages'). Platform prerequisites (macOS Screen Recording, Linux mss/grim) are also stated with the failure mode.

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