screenshot_page

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the output is a base64-encoded PNG, which is useful, but doesn't disclose side effects (navigation state changes), whether the viewport is scrolled during capture, or potential preconditions like requiring a loaded page. Given the moderate complexity (browser interaction), this is a notable gap but partially mitigated by declaring the format.

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 efficient sentence: 'Capture a PNG screenshot of the current page (base64).' It states the verb, resource, format, and encoding in minimal words. No wasted effort.

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 simple capture tool with 2 optional parameters and no output schema, the description is reasonably complete for the core purpose. However, the optional 'url' parameter behavior (navigating first) and 'full_page' semantics could disrupt expected output, and there's no output schema to clarify the return shape. The description adds the base64 detail but doesn't cover edge behaviors like unloaded pages or navigation side effects.

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?

The schema has 2 params with only 50% coverage. 'url' has a schema description ('Optional URL/path to open first'), but 'full_page' has no description in the schema, and the tool description doesn't explain it either. For a boolean that significantly changes the captured output (full page vs. viewport), the lack of elaboration is a gap. The description adds no param meanings beyond schema.

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 uses a specific verb+resource: 'Capture a PNG screenshot of the current page (base64).' It clearly distinguishes this from sibling navigation/search tools. Among many sibling tools (navigate, get_profile, search_jobs, etc.), this is the only screenshot tool, so differentiation is naturally clear.

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's no guidance on when to use this tool vs alternatives. It doesn't state when a screenshot is appropriate, whether it can be used mid-navigation, or how it relates to 'navigate' or the browser tools. Given it's the only screenshot tool among siblings, some context about typical use (e.g., after navigation, for verification) would help but isn't present.

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