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

The annotations already declare this read-only, idempotent and closed-world, so the description's job is only to add context, and it does: it explicitly states the tool performs no action itself ("opens nothing by itself") and returns screen/button/field-level instructions for the agent to execute via the browser tools. The note that Kalodata has a credit-billed official API adds cost-relevant context an agent would not otherwise have. Minor gap: it does not say how large or structured the returned walkthrough is.

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?

The critical fact (that it only returns instructions) sits in the middle of sentence two, after a misleading first sentence, so the description is not front-loaded. The closing sentence about the official API and per-credit billing is useful but reads like vendor copy appended to the action description. Three dense sentences with some promotional 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?

With zero parameters, no output schema and full annotation coverage, the description carries only the burden of explaining what comes back and what to do next, and it does both (step-by-step screens/buttons/fields, then run the browser tools). It stops short of describing the shape of the returned guide or whether it differs by account plan, which would complete the picture.

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 there is nothing for the description to disambiguate; baseline is 4. It correctly implies the tool is call-and-return with no scoping inputs such as account, category or date range.

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?

"List top shops in the user's own Kalodata account" names a resource and region, but the second sentence reveals the tool does not actually list anything: it "Returns how to do it in Kalodata step by step... and opens nothing by itself." The verb in the name/title conflicts with the real behaviour, so an agent must read past the first sentence to learn that this is a how-to-instructions tool, not a data-fetch tool. The underlying purpose is eventually clear, but the framing buries it.

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 does give the follow-on workflow: call this, then execute the steps with the cotlet_browser_* tools in the user's Kalodata Cloud Browser, which is genuinely helpful routing. It also notes Kalodata has an official Open API with ranking and detail endpoints billed per credit, giving an alternative. But it never says when to use this versus the sibling kalodata_list_top_creators / kalodata_list_top_products / kalodata_get_shop_details tools, nor when the paid API would be preferable to the browser path.

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