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

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), yet the description adds real value beyond them: it states explicitly that nothing is opened or executed, that the return is step-by-step screens/buttons/fields, and that a separate browser-tool layer performs the action. The API-availability note explains why the browser path is required, which is meaningful behavioral context not present in any structured field.

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 opening clause largely restates the tool name, and the closing API-audit narrative (specific 404 paths and a dated search) is verbose relative to a zero-parameter guidance tool. The middle sentence carries the genuinely useful information — returns steps, opens nothing, use cotlet_browser_* — but it is buried in a run-on chain 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 output schema and no parameters, the description must carry more weight; it does explain the return shape and the required follow-up tooling, which is the essential part. It omits whether the guidance is generic or tied to a specific customer and whether any preconditions (logged-in session, account selection) must hold before the browser tools can be used.

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 adds nothing about inputs because there are none, though it also does not note that the returned steps are therefore generic and not scoped to a specific customer — a minor missed clarification.

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 a crucial mode: it 'Returns how to do it in EZ Lawn Biller step by step' and 'opens nothing by itself', so the agent knows this is a procedural-guidance tool, not an action tool. However, the verb 'use' is vague against siblings such as bill_the_customer, edit_customer, or customer_search — the description never states which customer operation the steps cover, so the agent cannot tell exactly what task this guide addresses.

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?

Usage is implied: call this for guidance, then execute with cotlet_browser_* tools in the user's EZ Lawn Biller Cloud Browser. No alternative is named and no condition is given for choosing this over sibling tools like create_customer or customer_search, so routing depends on inference from the tool name.

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