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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety bar is low. The description still adds real value beyond them by stating that the tool 'opens nothing by itself' and that the actual work must happen through cotlet_browser_* tools in the cloud browser — the distinction between advisory and acting is the key behavioural fact here. It doesn't say anything about the shape or detail level of the returned steps, which caps it below 5.

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 one sentence that matters — instructions only, then act via cotlet_browser_* — is front-loaded, but the trailing API-audit narrative (404s on /api, /developers, /docs, FAQ naming QuickBooks, a specific date of 11 Nov 2026) is disproportionate detail for the payload. It's readable but padded for a tool that takes no arguments.

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?

There is no output schema, and the description does explain what comes back (step-by-step screens/buttons/fields) and how to use it, which is the right coverage for a zero-parameter advisory tool. The one gap is the split of responsibility with the browser tools — how much of the workflow the steps cover versus what the agent must infer — which is not spelled out.

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?

Zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies the call needs no context beyond the user's account, which is consistent with an empty, closed input schema.

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 names a specific resource (proration in EZ Lawn Biller) and a specific deliverable: step-by-step instructions covering screens, buttons and fields. It also states the crucial scope limit ('opens nothing by itself'), which separates it from the action-performing siblings. It is slightly muddied by leading with boilerplate about ChatGPT/Claude/any AI agent, but the core purpose is unambiguous.

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 next after calling it ('then do it with the cotlet_browser_* tools in the user's EZ Lawn Biller Cloud Browser') and explains why this route exists (no public API). What's missing is an explicit 'do not call if you already know the steps' or a named alternative among the many ez_lawn_biller_* siblings, so routing between this and e.g. bill_now is left to inference.

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