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

Annotations already cover read-only/idempotent/non-destructive safety, but the description adds genuinely new behavioral facts: billing accrues per started minute and the session expires three minutes after the last call. It does not state the failure mode when no browser session is open, which is the one behavioral gap.

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?

Return value is front-loaded in the first clause and the cost/session caveat follows immediately. Two sentences, no filler, though the 'boards, canvases and layouts' list is slightly vague padding.

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 zero-parameter tool with rich annotations and no output schema, the description supplies the return format (JPEG plus URL and title) and the session economics. The only omission is what happens when no browser is open, which is minor given the sibling set includes cotlet_browser_open.

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?

Zero parameters, so the baseline is 4; there is nothing for the description to compensate for and it introduces no misleading parameter language.

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?

States a specific verb+resource ('Returns a JPEG image of the visible part of the current page') and scopes it to visual content the page text does not show, which cleanly separates it from cotlet_browser_read without requiring the agent to open either schema.

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 phrase 'boards, canvases and layouts that the page text does not show' implicitly tells the agent to prefer the text-reading sibling and reach for this only for visual content. It stops short of naming cotlet_browser_read or saying what to do when no browser session exists.

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