browser_screenshot

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

Without annotations, the description carries the burden. It discloses the output format (PNG) and the two capture modes (full page or element), but it does not explain what the tool returns (e.g., base64-encoded image, file path), any side effects, or failure behavior. The basic behavior is clear, but important details are omitted.

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?

The description is a single sentence that instantly communicates the core action and options. It is front-loaded with the verb and resource, contains no redundancy, and every phrase earns its place.

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?

The tool is simple with only two optional parameters, and the description covers the primary purpose and high-level options. However, it lacks details about the output format and return value, which is especially important because there is no output schema. Edge cases and parameter interactions are also unaddressed, leaving the description sufficient but not thorough.

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 0%, so the description must compensate for parameter meaning. It mentions 'full page' and 'single element', which map conceptually to fullPage and selector, but does not explicitly name the parameters, their types, or how they interact (e.g., precedence when both are provided). It provides partial but not full semantics.

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 clearly states the tool's action ('Capture a PNG screenshot'), the resource ('current page'), and optional scope ('full page or a single element'). It is specific and distinct from sibling tools that navigate, click, fill, or evaluate, leaving no ambiguity about what this tool does.

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?

No guidance is provided on when to use this tool versus alternatives. It does not mention any preconditions, such as needing a page to be loaded, nor does it differentiate from other inspection methods like browser_get_text or browser_snapshot. The description simply states the function without context for use.

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