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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false; "opens nothing by itself" merely restates that safety profile. The genuinely additive part is the output shape (step-by-step screens, buttons, fields) and the handoff to browser tools, useful since no output schema exists, though it is unclear whether the guide is account-specific.

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 lead sentence wastes space on "from ChatGPT, Claude or any AI agent," and the closing API/pricing note ("only on paid plans, checked 14 Oct 2026") does nothing to help an agent invoke this tool. The operative facts — that it returns a guide and opens nothing — are buried mid-sentence rather than front-loaded.

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 parameters, no output schema, and rich annotations, the definition covers enough to call it safely and knows the next step is cotlet_browser_*. It still leaves open whether the returned guide is specific to the user's account and how it differs from the paid Holded API it advertises.

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 4 applies. The empty schema with additionalProperties=false confirms no inputs are needed.

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 name and title say "List unpaid invoices," but the description reveals the tool actually returns step-by-step instructions ("screens, buttons, fields") rather than invoice data, and explicitly states it "opens nothing by itself." The return behavior is stated, but the verb/resource framing conflicts with the real function, so an agent must read carefully to learn it is a guide, not a lister.

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 description gives a usable sequence: get this guide, "then do it with the cotlet_browser_* tools in the user's Holded Cloud Browser," which is real when-to-use guidance. It offers no exclusions and never says when to skip this in favor of the native Holded API it mentions, leaving the alternative path unaddressed.

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