crawl_screenshot

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

With no annotations, the description carries full burden. It discloses that the screenshot is ephemeral (returns an ephemeral screenshot_url), explains that store=true persists the HTML page (not the screenshot), and notes storage scoping to JS token. It does not mention rate limits or auth beyond token hint, but provides key behavioral context.

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 sentences with no waste. First sentence states main action, second sentence adds the critical nuance about store parameter. Information is front-loaded and every word adds value.

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?

Given the tool has 7 parameters and no output schema, the description covers the main behavior but does not explain return format (beyond mentioning screenshot_url) or common use cases for parameters like mode, device, page_wait. It is adequate but could be more complete for an agent to invoke correctly without schema cross-referencing.

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 coverage is 100%, so baseline is 3. The description adds value by clarifying the store parameter behavior (persists HTML, not screenshot) and mentioning the use_js_token requirement, which is not in the schema description. This exceeds minimal schema explanation.

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 takes a screenshot of a webpage, distinguishing it from sibling tools like crawl and crawl_markdown which have different purposes (crawling and markdown extraction). The verb 'Take' with resource 'screenshot of a webpage' is specific and unambiguous.

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 provides guidance on using the store parameter (when to persist HTML) but does not explicitly state when to use this tool over siblings like crawl or crawl_markdown. It implies usage for visual capture but lacks explicit when-not or alternative comparisons.

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