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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), and the description adds real beyond-schema context: the base64 JSON return shape, the bot-protection limitation, and a cost note that failed/blank captures aren't charged. These are behaviors an agent cannot infer from annotations alone.

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?

A single dense, front-loaded paragraph: identity and return format first, options next, limitations and billing last. No filler sentences; every clause carries information.

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 10-parameter tool with full schema coverage and no output schema, the description supplies the missing pieces: return format, the key limitation, the alternative tool, and cost behavior. Nothing essential to calling it correctly is left out.

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 baseline is 3. The description only loosely gestures at options ('viewport, full page, dark mode, selector'), which map to parameters the schema already documents in more precise terms, so it adds little beyond the structured fields.

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+resource (screenshot a URL) and enumerates the output formats (JPEG, PNG, WebP, PDF as base64 JSON), so the agent knows exactly what it gets back. It also routes away from itself by naming the sibling 'unblock' for bot-protected pages, cleanly separating it from related tools.

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?

Provides an explicit exclusion ('does not get past bot protection') paired with the correct alternative ('use unblock for those pages' text'). It lacks broader when-to-use framing versus other capture-ish siblings, but the failure-case routing is clear and actionable.

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