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

With no annotations, the description carries the full behavioral burden. It usefully discloses the default output directory and the SCREENSHOT_OUTPUT_DIR override, but says nothing about failure modes (unreachable URL, selector timeout), whether the browser is launched locally, or what the tool actually returns (file path vs. image payload).

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?

Two short sentences: the capability first, then the output-destination detail. Zero filler, nothing buried.

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 an 8-parameter, annotation-free tool with no output schema, the definition covers placement of the artifact but not the return contract — an agent cannot tell whether it gets a path, a base64 image, or a success flag. The dependency between selector and fullPage is also left unresolved.

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 every parameter is self-documented, so baseline is 3. The description adds only one piece of extra meaning — the default output location and env-var override for outputPath — and it does not clarify the interaction between fullPage and selector or how waitForSelector and waitForTimeout combine.

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+resource ("Capture web page or element") plus the mechanism (headless browser), which is enough to separate it from take_system_screenshot. It never names the sibling explicitly, so the differentiation is inferred rather than declared.

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?

"web page or element" hints at the domain, but there is no explicit statement of when to prefer this over take_system_screenshot (which captures the local screen) or any prerequisites/exclusions. The agent must reason about the alternative on its own.

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

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

With no annotations, the description carries the full burden and does a good job: it names the concrete backend per platform (screencapture, maim/scrot, PowerShell+.NET), states the default save path and the SCREENSHOT_OUTPUT_DIR override. It omits notable behavioral facts such as macOS screen-recording permission requirements and whether the saved file path is returned, which keeps it below a 5.

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?

Three sentences, front-loaded with the action, then platform backends, then output location and mode prerequisites. No filler, though the platform backend enumeration is somewhat dense detail an agent rarely needs to act on.

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 9-parameter tool with a nested region object, no annotations, and no output schema, the description covers intent and storage location but says nothing about the return value (e.g., whether the file path is returned) or permission prerequisites. The minimum needed to invoke is present; the minimum needed to interpret the result is not.

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 every parameter is already documented in the schema, including mode, region, windowName and windowId. The description's only added parameter context is the windowName-by-app-name example, which largely duplicates the schema text. Baseline 3 is warranted.

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 desktop, window, or region screenshot') and enumerates the three capture modes, so the agent knows exactly what the tool produces. It does not differentiate itself from the sibling tool take_screenshot, which leaves the naming distinction unresolved.

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 explains mode prerequisites ('For window mode, provide windowName or windowId'), which is useful routing within the tool, and gives the default output location. However, it offers no guidance on when to choose this tool over the sibling take_screenshot, and no exclusions or failure conditions are described.

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