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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds the non-obvious behavior that matters most: the tool performs no action and opens nothing, it only returns a step-by-step procedure. It still omits whether the account connection must be established first and what exactly the returned payload looks like.

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 key point, that it returns steps and performs nothing, is front-loaded in the first sentence. The phrase 'from ChatGPT, Claude or any AI agent' is filler that adds no selection value, though the final sentence justifies the browser-automation path and earns its place.

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 input schema, no output schema, and no parameters, the description carries the whole burden and mostly meets it: it explains the return content and points to the companion browser tools for execution. The main gap is the handoff mechanics, specifically whether a Yardbook Cloud Browser session must exist before the returned steps are actionable.

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, which is the baseline-4 case. The description is consistent with a no-argument guide call, but it never tells the agent how the invoice details are conveyed, which by construction has to be natural-language context rather than structured input.

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 description states a specific verb and outcome: 'Returns how to do it in Yardbook step by step (screens, buttons, fields) and opens nothing by itself.' That tellingly reframes the tool from 'create invoice' to 'return instructions', which an agent needs. It does not differentiate itself from the sibling cotlet_app_guide, which could plausibly return the same kind of guidance.

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 clearly sequences the workflow: get the steps here, then execute them with the cotlet_browser_* tools in the user's Yardbook Cloud Browser. There are no explicit exclusions or prerequisites (for example, whether a browser session must already be open), so it stops short of full when/when-not guidance.

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