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

Goes well beyond the readOnly/idempotent annotations: it discloses privacy limits (field values, cookies and storage are never returned), a 20,000-character truncation cap, scroll-relative positioning on long pages, per-minute credit cost, and a 3-minute session idle timeout. These are exactly the operational facts an agent needs before calling.

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?

Four sentences, each carrying unique information — return contents first, then exclusions, then truncation/scroll, then cost and lifetime. No repetition of the title and 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 must carry the return contract, and it mostly does (text + element list, exclusions, truncation). It does not describe the element-list format (e.g. whether the numbering is directly usable as a selector for cotlet_browser_click), which is the one gap for an agent driving a browser.

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?

The tool takes zero parameters, so the baseline is 4; there is no parameter syntax to explain. The description correctly spends its words on output shape and session behavior instead.

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 and resource ('Returns the current page of the user's Substack Cloud Browser') and enumerates exactly what comes back: readable text plus a numbered list of links, buttons and fields. This clearly separates it from siblings like cotlet_browser_screenshot (pixels) and cotlet_browser_click (action).

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 mention of a 'numbered list of its links, buttons and fields' implies this is how you discover what to click or type next, and the scroll note implies when the output is offset. But no explicit when-to-use statement or named alternative (e.g. screenshot vs read) is given, so usage must be inferred.

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