Screenshot

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so safety is covered. The description adds useful context about the output format (PNG via the 'universal' target) and a docs link, but does not say how the image is delivered (URL vs base64), whether existing data is affected, or any rate/latency expectations.

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 tight sentences: capability plus backend detail first, disambiguation and docs second. No filler, and the most decision-relevant information is front-loaded.

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 two-parameter read tool with rich annotations but no output schema, the description covers purpose, selection criterion, and output type. The one remaining gap is the shape of the returned artifact (image payload vs URL), which is only inferable via the docs link.

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 both `url` and `geo` are already documented in the schema. The description adds nothing about geo behavior or URL formatting, so the baseline 3 applies.

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 and resource ('Capture a PNG screenshot of a web page') plus the backend mechanism ('universal' target with PNG output). The second sentence draws a clear line against the text-scraping sibling by explaining the visual-vs-text distinction.

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 an explicit selection criterion: use when layout or visuals matter rather than text only, which implicitly routes text extraction to scrape_as_markdown. It stops short of naming that sibling tool or stating exclusions (e.g., dynamic-page caveats, cost/latency tradeoffs).

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