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

With annotations containing only a title, the description carries the full disclosure burden — and it does useful work: it reveals the output is a URL (not image data), that the default is a single screenful, and that 'full' extends capture past the first screenful. The 'photograph' metaphor also implies a non-mutating snapshot. It doesn't mention auth, rate limits, or failure behavior, leaving a modest gap.

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 action and return type are front-loaded in the first sentence, and the subsequent clauses each earn their place (selection semantics, full-page behavior). The middle examples could be tightened, but overall it is appropriately sized with no filler.

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 small read-only tool with no output schema, the description covers the essential selection criterion, the return-type convention, and the screenful-vs-full behavior. The 'wait' parameter's job remains conveyed by the schema alone, and edge cases (unrenderable pages, timeout) are minor gaps; nothing confusing 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 description coverage is 100% and each parameter already has a clear description, so the baseline of 3 applies. The description only paraphrases 'full' ('capture past the first screenful'), adding no genuinely new meaning for 'url' or 'wait'.

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 ('Photograph a page') and a concrete result ('get back a URL for the picture'). 'What it looks like, rather than what it says' clearly distinguishes it from text-reading siblings like browser_read, so an agent can select the right tool without opening schemas.

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 visual use-cases (chart, layout, page whose content is an image) and the 'rather than what it says' formulation implies text extraction is not the job of this tool. It never explicitly names the alternative (browser_read) or states a when-not-to-use rule, so context is clear but routing is implicit rather than explicit.

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