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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the description's added value is in the details it supplies: the 20,000-character cap, that open dialogs are listed first, and that field values, cookies and storage are never returned. The one omission is what an agent should do when the cap truncates the page — there is no guidance on continuing past 20k characters.

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, front-loaded with the primary behavior and return payload, then the usage rule and the exclusions. Every clause carries information; there is no filler.

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?

With no output schema, the description does the work of describing the return shape (text plus a numbered control list) and the privacy exclusions, which is adequate for a one-parameter read tool. The gap is the truncated-content path: nothing tells the agent how to read beyond the 20,000-character limit.

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 100% for the single `element` parameter, so the baseline is 3. The description adds only a parenthetical gloss on what an element can be ("a dialog, a form, a list"), which is mildly helpful but largely restates the schema's "Read only inside this element."

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 whole current page: its text (up to 20,000 characters) and a numbered list of its links, buttons, fields and other controls" names a specific verb and resource and enumerates the exact return contents. It also distinguishes this full-page read from the narrower `element` mode and, implicitly, from capture-style siblings like screenshot or find.

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?

"Use it on a new page or when a step's answer is not enough" gives an explicit trigger, and the `element` clause states the alternative and its scope. It stops short of routing against other siblings such as cotlet_browser_find, cotlet_browser_evaluate or cotlet_browser_screenshot, which an agent may also consider for inspecting a page.

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