visual_capture

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

Annotations are sparse (readOnlyHint false, destructiveHint false), so the description carries the burden. It adds a behavioral statement ('Does not navigate'), a prerequisite ('requires lease_id and an open browser session'), and a return type ('metadata + MCP ImageContent'), providing useful context beyond the structured fields. No contradiction with annotations.

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?

Three concise, front-loaded sentences with zero redundancy. Every sentence adds either core purpose, parameter behavior, prerequisites, or a side-effect disclaimer.

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 six-parameter tool with no output schema and no schema descriptions, the description covers the main behavior, prerequisites, navigation side-effect, and return type. The main omission is the mode/selector relationship and how width/height interact with device presets, making it slightly incomplete but still robust.

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%, so the description must compensate. It explains the core parameters: mode (viewport/element/full_page), width/height as optional overrides of device presets, and lease_id as required. However, it fails to connect the selector parameter to the 'element' mode, leaving a critical dependency 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?

The description states the action ('Capture a PNG screenshot'), the resource ('current browser page'), and the three modes (viewport/element/full_page), making it immediately distinguishable from sibling tools like browser_snapshot (likely DOM) and visual_get (may retrieve existing screenshots).

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?

It provides clear context: requires lease_id and an open browser session, and explicitly states it does not navigate. However, it does not name alternative tools like visual_get or visual_compare or state when to prefer one over another, so it stops short of full when/when-not guidance.

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