capture_screenshot

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

The description discloses key behaviors beyond annotations: consumes audit quota, implemented via audit_url (not lightweight), and hints are advisory. Annotations only say readOnlyHint=false, which aligns with the consumption note, no contradiction.

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 concise (two sentences) and front-loaded with the main purpose. The prefix '[session]' adds context, and every sentence contributes meaningful information. Could be slightly more structured, but overall efficient.

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 11 parameters and the presence of an output schema, the description adequately covers core behavior (screenshot+audit, quota consumption, advisory hints). It explicitly notes the implementation via audit_url, which provides context among siblings. Minor gap: no mention of return format, but 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?

Although schema coverage is 100% (baseline 3), the description adds value by clarifying that hints (viewport, fullPage, etc.) are advisory and not guaranteed to be honored. It also highlights mode='basic' as most cost-effective, aiding parameter selection.

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 clearly states the tool's purpose: 'Capture a hosted screenshot of a URL plus the full audit result.' This is a specific verb+resource+outcome, distinguishing it from lightweight screenshot tools by emphasizing it includes an audit.

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 offers a usage tip ('Use mode='basic' for cheapest') but lacks guidance on when to use this tool versus siblings like audit_url or run_audit. No explicit when-not-to-use or alternative comparisons are provided.

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