Screenshot

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

Annotations already declare readOnlyHint and openWorldHint=false, and the description adds genuinely new behavior: images are downscaled to maxWidth for token economy, savePath swaps the return channel from image content to a file write, annotate overlays numbered ref boxes, and it works on background tabs. Those are exactly the traits an agent needs that no structured field conveys.

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 short sentences, front-loaded with the primary purpose, then the annotate mode, then the cost/return controls. Every clause carries information an agent would otherwise have to infer; nothing is repeated from the schema verbatim.

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?

With 8 optional params, 100% schema coverage, no output schema, and safety already covered by annotations, the description closes the remaining gaps: it explains the annotate workflow, the two return modes (inline image vs saved file), token cost behavior, and background-tab support. Nothing needed to invoke it correctly is missing.

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 the baseline is 3; the description earns above that by explaining the intent behind annotate (Set-of-Mark overlay for pointing), maxWidth (token-saving downscale), and savePath (file instead of returned image) rather than just restating types. It does not add detail on format/quality tradeoffs already covered by the 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?

Names a concrete verb+resource ('Captures') and enumerates the three capture scopes (viewport, full page, one element), which maps directly onto fullPage/ref/neither. The Set-of-Mark annotation behavior and 'works on background tabs' clause further separate it from the DOM-oriented siblings like page_snapshot and page_read.

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?

Gives clear situational guidance inside the sentence: use annotate=true when you need to point at elements, use savePath when you want a file instead of an inline image. It never explicitly routes away from an alternative (e.g. pdf_save or page_snapshot when refs are needed), so no exclusions are stated, but the conditions for each mode are unambiguous.

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