capture_page_screenshot

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

The description adds substantial behavior beyond the annotations: an attached MCP image is always returned, base64 is only present when requested, image dimensions are device rather than CSS pixels, and size means byte count. These are non-obvious and prevent incorrect interpretation. It does not contradict the destructiveHint annotation; the save_path write behavior is acknowledged.

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?

Four dense sentences, front-loaded with the core action and modifiers, then essential caveats. Every sentence adds distinct value, with no filler or repetition. The only minor jargon is 'page-specific API,' but it is acceptable in context.

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 no output schema, the description covers the most critical pitfalls: output side-channel behavior, disk-writing semantics, pixel units, and model-image limitations. It leaves tab/session selection and timeout semantics implicit, but these are partially supported by sibling tools and self-explanatory defaults.

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?

With 0% schema description coverage, the description carries the burden for 9 parameters. It explains format/quality, full_page, clip, save_path, and return_base64, but leaves timeout, tab_id, and session_id semantics implicit. Some mentioned fields like image_width/image_height appear to describe return metadata rather than input parameters, so parameter coverage is partial.

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 opens with a specific verb and resource: 'Capture a viewport, full-page, or clipped screenshot of a page/tab via CDP.' It clearly enumerates the tool's modes and contrasts it with page_click on pixel semantics and with scan_page/execute_js on image-consumption limitations, so an agent can distinguish it from siblings.

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?

It explicitly states when not to rely on the result: if the model cannot consume images, it has not seen the pixels and must use scan_page, execute_js, a page-specific API, or OCR instead. It also clarifies that save_path only controls disk output and the MCP image is still returned, preventing a likely misuse.

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