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

Annotations already note idempotency and non-read-only status; the description adds valuable behavioral context beyond that: it costs 1 credit regardless of options, it runs JavaScript and loads web fonts/images, and it renders exactly like a browser. It also discloses that page_options affect downstream artifacts (ads and banners removed from html, markdown, and summaries). No contradiction with annotations.

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 front-loaded with the core action, then purpose, then parameter summaries, with no redundant filler. Every sentence earns its place: the first identifies the endpoint and behavior, the second scopes usage, and the third organizes the nested option groups. It is structured for quick scanning.

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 a complex 10-parameter tool with nested objects and no output schema, the description covers the essential behavioral context: what is captured, rendering fidelity, pricing, and how the two main option groups affect the result. It does not need to explain return values because the schema already documents sync/async behavior, and annotations cover idempotency. Slightly more could be said about error cases, but this is adequate.

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 the schema fully documents all 10 parameters. The description adds useful grouping and intent—'screenshot_options size it... encode it... restyle it' and 'page_options wait for the page and take ads and cookie banners out of it'—but these are summaries, not new parameter semantics. This meets the baseline 3 without exceeding it.

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 opens with a specific verb and resource: it 'Captures the whole rendered page as a PNG', and clarifies rendering fidelity ('JavaScript executed, web fonts and images included, exactly as a browser would draw it'). It also distinguishes itself from read-oriented siblings by saying 'Use it to see a page rather than read it', making the tool's purpose unmistakable.

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 gives explicit use cases ('layout, visual regressions, link previews, or checking what an anti-bot page actually showed us') and sets a clear rule of thumb: use it to see rather than read a page. It stops short of naming specific sibling tools or stating when not to use it, but the 'rather than read' contrast implicitly routes text-extraction tasks elsewhere.

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