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

The description adds real context beyond annotations: it opens nothing, returns step-by-step instructions with screens/buttons/fields, and explains why browser tools are required (no official API, webhooks or Zapier). That said, the text is partly promotional and repetitive, and it says little about what the guide output contains or how to recover if the UI differs.

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 core operational detail is correct but the opening clause ('from ChatGPT, Claude or any AI agent') is filler, and the key constraint ('opens nothing by itself') is mid-sentence rather than front-loaded. It could say in one line: returns a walkthrough, performs no action, use cotlet_browser_* to execute.

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?

For a zero-parameter guide tool, it covers the essentials: what it produces and what to do next. It omits, however, any statement of the output shape and whether the guide is account-specific, and its naming ambiguity risks the agent treating it as a data-returning list operation.

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?

There are no parameters, so parameter semantics are not the main issue. Score reflects that the description doesn't clarify what inputs the surrounding browser steps need or how they relate.

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 does clarify the actual function, but only after the name and title ('List customers') imply the tool retrieves customer data. An agent skimming before reading would form the wrong expectation; the sentence 'Returns how to do it in Klean CRM step by step' is the real purpose and is buried behind a copied name.

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 tells the agent what to do afterwards ('then do it with the cotlet_browser_* tools in the user's Klean CRM Cloud Browser'), which is useful sequencing guidance. But it never says when to pick this over siblings like cotlet_app_guide or when a direct CRM tool would be preferable, nor what to do if a step fails.

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