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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds the key non-obvious behavior that it 'opens nothing by itself' and only returns instructions, which prevents an agent from assuming the invoice listing has already occurred. The trailing paragraph about Supermove's Developer API is unrelated to this tool's behavior and adds noise rather than transparency.

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 useful content is two clauses at the start, but the definition is padded with client-name marketing ('from ChatGPT, Claude or any AI agent') and a long, tangential paragraph about Supermove's Developer API endpoints, including an oddly specific verification date. That API paragraph does not help an agent decide or call this tool and should be cut.

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 annotations covering safety, the description carries the right amount of load: it tells the agent what comes back (a step-by-step guide) and hands off to the cotlet_browser_* tools for execution. Minor gap: it does not say whether the returned guide is tied to a specific page or how the agent should sequence the subsequent browser calls.

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 no parameters, so there is nothing parameter-level to document and the baseline applies. The description correctly implies the scope is fixed to 'the user's own Supermove account' with no filtering options available.

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 outcome: it returns a step-by-step Supermove walkthrough (screens, buttons, fields) and explicitly does not perform the action itself. This resolves the ambiguity in the tool name 'list_invoices', which would otherwise suggest it returns invoice data. It falls short of 5 because the first sentence still frames it as 'List invoices... from ChatGPT, Claude or any AI agent', which re-introduces the misleading reading before correcting 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 gives one concrete next step ('then do it with the cotlet_browser_* tools in the user's Supermove Cloud Browser'), which is genuine routing guidance. However, it never states when to prefer this over cotlet_app_guide or the other supermove_* siblings, nor what prerequisites exist (e.g., an open browser session) before calling it.

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