browser_screenshot

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

With no annotations, the description carries the full behavioral burden and largely restates the schema fields. It never says what the tool returns (base64 data, in-memory image, or a file), what happens when save_path is omitted, or whether the capture blocks on page load. These are material gaps for a screenshot tool.

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 front-loaded sentence enumerating the three capture modes with zero waste. Well sized for the tool's scope.

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?

Adequate for parameter selection but incomplete for invocation: with no annotations and no output schema, the agent has no statement of the return value (image data vs. saved file) or the effect of omitting save_path. It should do more to cover the behavioral side that structured fields don't.

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 all three parameters are already documented in the schema; the description only mirrors the selector/full_page modes. Baseline 3 applies since the schema does the heavy lifting and the description adds no format or default details beyond it.

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 ('Capture screenshot') and resource ('current page, entire scrollable page, or a specific element'), which is clearly distinct from the many navigation/interaction siblings. It does not explicitly differentiate itself from the closest alternative, browser_snapshot, so it falls short of a 5.

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?

There is no guidance on when to prefer a screenshot over browser_snapshot, browser_get_html, or browser_print_to_pdf, and no preconditions (e.g., page must be loaded, tab must be selected). The three modes are listed but no condition indicates which to choose.

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