screenshot_to_clipboard

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

Annotations cover the safety profile (destructiveHint=false, openWorldHint=false, readOnlyHint=false), so the description need only add context; it does add that no file artifact is created. However, the two traits that matter most are missing: it silently overwrites whatever is currently on the clipboard, and 'a region' with zero parameters implies an interactive user-driven selection that may block the call. Neither is 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?

A single sentence with the action front-loaded and the key differentiator (clipboard, no file) in a compact parenthetical. No filler, nothing redundant.

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?

There is no output schema and no parameters, so the description carries the full burden for a zero-arg tool, and it omits the things an agent actually needs: whether the call blocks on user interaction, and whether it returns anything (dimensions, path, success flag). It is adequate to know what the tool does, but not to predict what invoking it will do to the session or the clipboard.

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?

Zero parameters, so the baseline is 4 and there is no schema surface for the description to compensate for. The one thing worth explaining — how the region is determined without any region argument — is left unaddressed, which is a small deduction from an otherwise trivially satisfied dimension.

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?

Specific verb + resource + destination: 'take a screenshot of a region' and 'copy directly to clipboard (no file saved)'. The 'no file saved' clause implicitly separates it from the screenshot_full/region/window siblings, which presumably write files, though it never names them. An agent can tell what the tool produces, but must infer the distinction from the sibling family rather than being told.

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 'no file saved' parenthetical implies the selection condition (want the image on the clipboard, not on disk), but no alternative is named and no explicit when-to-use guidance is given. No prerequisites or preconditions (e.g. an interactive selection step) are stated.

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