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

Beyond the annotations, the description discloses behavior an agent cannot otherwise know: cookie walls and pop-ups are hidden and never accepted unless show_popups=true, each picture consumes one read, and pictures are persisted to the user's Puley history. The persistence note meaningfully explains why readOnlyHint is false despite the tool being a visual inspection.

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 core output is front-loaded in the first clause, and the parentheticals are compact rather than verbose. It reads as one dense run-on sentence with nested asides, which slightly impedes scanning but wastes little.

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 six-parameter, no-output-schema tool, the description covers purpose, per-call cost, side effects, and five of six parameters adequately. Missing are the return shape (image versus links) and any error or failure behavior, which matter given no output schema exists.

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?

With 0% schema description coverage, the description carries the burden and does so for most parameters: device values (phone or desktop), country as a two-letter code with examples, countries as up to 4 codes rendered side by side, and the meaning of whole_page and show_popups. The required link parameter is never described (no URL format guidance), which is the main gap.

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 plainly states the resource and output: "A screenshot of a page in a real browser" and "The picture itself is returned," which implicitly separates it from text-extraction siblings like read_site. It does not name any sibling tool, so an agent must infer the boundary rather than being routed explicitly.

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?

Use cases are concrete: "checking how a site looks, whether a banner, price or button shows, or what visitors elsewhere see." That gives a clear context for invocation, but there is no explicit "do not use this when..." guidance or named alternative for cases where text extraction would be better.

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