web_screenshot

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

Annotations (readOnlyHint=true, openWorldHint=true) already signal a safe open-world read, so the description doesn't need to restate safety. It does add real behavioral context: anti-bot handling is 'like web_fetch', the return is a path plus an inline image by default, and the inline PNG is skipped above 3 MB. No permission or quota details, but nothing is contradicted.

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?

Three tightly packed sentences, front-loaded with the action and output, then routing, then flags. Every clause earns its place, though the flag explanations make it slightly denser than an ideal one-screen summary.

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?

There is no output schema, so the description carries the return-value burden and does: it states the returned path and the default inline image behavior, plus the 3 MB caveat. Combined with read-only annotations and 100% schema coverage, an agent has enough to invoke correctly; only niche details (tier semantics, proxy/profile interaction) are left to the schema.

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 goes slightly beyond the schema by explaining inline's 3 MB skip threshold and clarifying what full_page ('whole scroll height') and mobile ('renders it as a phone') actually change about the capture, which is genuinely useful framing for choosing flags.

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 specific verb and resource ('Save a PNG of a page rendered in a real browser') and immediately distinguishes it from siblings: web_snapshot for reading/acting, web_fetch for anti-bot handling parity. An agent can tell exactly what this produces (a PNG file path) without opening the schema.

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?

Explicit both ways: 'Use when the question is visual: layout, a chart, an image, how a page looks to a person' and 'To read or act on a page use web_snapshot instead: cheaper, and it gives refs, whereas a screenshot cannot be clicked.' This is a clear when/when-not with a named alternative and the tradeoff that selects it.

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