Auto-Browser

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

No annotations provided, so description carries full burden. It successfully conveys the 'lightweight' nature and comparative behavior vs observe. However, it fails to disclose critical behavioral details like return format (base64, file path, or binary), side effects, or blocking behavior.

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?

Single 12-word sentence that is front-loaded with the action. Every word earns its place—'lightweight' and 'without the full observe payload' provide essential differentiation without verbosity.

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 no output schema exists, the description should ideally explain return format (critical for a screenshot tool), which it omits. It covers the core function but leaves gaps regarding the label parameter and return value structure.

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 has 0% description coverage, requiring the description to compensate. It implicitly contextualizes 'session_id' via 'for one session', but completely ignores the 'label' parameter and its default value 'manual', leaving half the parameters undocumented.

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?

Uses specific verb 'Capture' with resource 'screenshot' and clearly distinguishes from sibling tool 'observe' by stating it excludes the 'full observe payload'. The phrase 'for one session' also links clearly to the session_id parameter.

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 implicit guidance by contrasting with 'observe' (lightweight vs full payload), suggesting it's for quick visual checks. However, lacks explicit when-to-use/when-not-to-use statements or clear alternative recommendations.

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