browser_vision

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

No annotations provided; description captures read-only behavior and explains parameter effect (full page vs viewport). Could mention session requirement but adequate.

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?

Two sentences plus bullet-pointed args; purpose stated first, no wasted words.

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?

Covers when to use, parameters, and effect; output schema exists so return format not required. Sufficient for a simple screenshot tool.

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 0%, but description explains session_id and full_page meaning, adding context beyond default titles and values.

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?

Description states 'Take a screenshot' and specifies use cases (CAPTCHAs, complex layouts, when text snapshot not enough), clearly distinguishing from sibling browser_snapshot.

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?

Explicitly tells when to use (visual inspection) and implies when not (if text snapshot suffices), providing clear context and alternative.

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