Auto-Browser

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

With no annotations provided, the description carries full burden. It successfully discloses the 'perception summary' aspect (implying AI processing) and 'interactables' detection, but fails to state whether this is read-only, computationally expensive, or blocking. It hints at behavior but lacks operational safety context.

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, front-loaded sentence with no redundancy. Every component listed (screenshot, interactables, perception summary) serves to differentiate the tool. Brief but not wasteful, though arguably too concise given the information gaps.

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?

Adequate for a simple observation tool but incomplete given the lack of output schema and param descriptions. The description explains what data is gathered but not the structure of returned data, the meaning of 'limit', or error conditions. Minimum viable but clear gaps remain.

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 0% and the description adds no parameter context. While 'session_id' is self-evident, 'limit' is ambiguous—it likely constrains the number of interactables returned, but this critical semantic is undocumented in both schema and description.

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 uses a specific verb ('Capture') and clearly identifies the composite output (screenshot, interactables, perception summary). It implicitly distinguishes from sibling tools like 'screenshot' (which lacks interactables/summary) and 'find_elements' (which lacks screenshot/summary) by detailing its unique triple-output nature.

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?

No explicit guidance on when to use this versus alternatives like 'screenshot', 'get_html', or 'find_elements'. Given the numerous sibling browser tools, the description should clarify that this is for comprehensive state observation rather than specific element queries or raw data extraction.

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