Screenshot a Roblox window

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context: execution happens on the SERVER host, it is Windows-only, it uses user32 GetWindowRect plus System.Drawing.CopyFromScreen, and a file is written to the temp directory when no savePath is supplied. What it does not add is failure behavior (it defers to tool-schema), which is explicitly pushed elsewhere.

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 action, result, and platform constraint in the first sentence, followed by targeting and implementation detail. It is dense but well ordered; the trailing boilerplate 'On failure: inspect tool-schema...' and the restated Signature line are redundant padding against the compact JSON schema.

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?

For a 3-parameter read-only tool with no output schema, the description covers everything an agent needs: targeting semantics, platform limitation, side effect (file written), default destination, and the returned fields { savedPath, width, height }.

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%, so the schema already documents all three parameters and the baseline is 3. The description adds meaning beyond the schema by specifying the resolution order between processId and windowTitle, including the default of 'the single Roblox window if neither is given,' which the schema does not state.

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 (capture an OS screenshot of a Roblox window, save as PNG, return path and dimensions) and distinguishes it from siblings like list-roblox-windows and observe-world. The scope (server host, Windows-only) and the exact return shape are named, so an agent can identify it without opening the 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 a concrete routing rule: 'Use list-roblox-windows first when several windows are open,' naming the alternative and the condition that selects it. It also explains the no-argument default (single Roblox window). It does not discuss when this tool is inappropriate (e.g., vs. in-game capture tools like observe-world), so it stops short of full when/when-not guidance.

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