Take a screenshot

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

With no annotations, the description carries the full behavioral disclosure burden. It does disclose that region/windows modes require interactive selection (potentially blocking) and that 'save returns and verifies a PNG path' and 'copy writes only to the clipboard'—these are useful traits. However, it omits any behavior for the 'slurp' action and does not explain what 'smart' mode does or how fullscreen behaves. It also doesn't mention side effects (e.g., clipboard overwrite) or return values for copy/slurp, so coverage is partial.

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?

The description is compact—two sentences—and the first sentence immediately states the primary action. The second sentence efficiently bundles mode and action behaviors. It is front-loaded and without fluff. Minor point: the phrase 'region/windows require an interactive selection' could be read as covering both modes clearly, but it's slightly ambiguous whether 'windows' refers to the 'windows' enum value or the OS windows; still, the overall structure is effective.

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?

Given only two parameters with enums, no output schema, and no annotations, the description ought to fully specify all behaviors. It covers save/copy distinctions and notes interactive selection for two modes, but leaves 'smart' and 'fullscreen' undefined and 'slurp' entirely missing. Return types for copy and slurp are not described. This is insufficient for an agent to confidently choose and invoke the tool across all valid modes and actions.

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 0%, so the description must explain both parameters. It clarifies that 'region/windows' modes interactively select an area and that 'save' returns a verified path while 'copy' goes to clipboard. However, it leaves the 'smart' and 'fullscreen' modes unexplained, and the 'slurp' action is completely unmentioned. The description adds some value but does not adequately compensate for the missing schema descriptions of half the enum options.

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?

The description clearly states the tool's purpose: 'Take a screenshot.' It also begins to distinguish modes (region/windows require selection) and actions (save vs copy), which gives the agent a concrete sense of scope. However, it never explicitly names sibling tools like capture_region_clipboard to differentiate them, so the purpose is clear but sibling separation is left indirect.

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?

The description gives no explicit guidance on when to use this tool versus alternatives. It mentions that 'region/windows require an interactive selection' as a caution, but does not state that for a quick region capture to clipboard, one should use capture_region_clipboard, or that fullscreen/smart are the defaults for automated capture. There is no when/why routing, leaving the agent to infer usage from the enum values.

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