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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful context beyond that: it explicitly says it opens nothing by itself and that its output is procedural instructions rather than data, and it discloses that no public EZ Lawn Biller API exists (citing 404s on /api, /developers, /docs and QuickBooks being the only named integration), which explains why a browser-driven approach is used. It does not describe response shape or length, which keeps it from a 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 core behavior and the follow-on tool are front-loaded, which is good. But the trailing paragraph about API research dated 11 Nov 2026 is bulky and reads as provenance notes rather than actionable guidance for an agent, and the opening sentence 'Preview in the user's own EZ Lawn Biller account from ChatGPT, Claude or any AI agent' spends words on client names that do not affect invocation.

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 and no output schema, the description carries the burden of explaining what comes back, and it does: step-by-step screens, buttons and fields. It also explains the handoff to the browser tools. The remaining gap is the lack of differentiation from the other preview siblings, which an agent would need to pick the right one.

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, so there is nothing for the description to disambiguate; the baseline for a parameterless tool is 4. The description correctly implies no inputs are needed by framing the tool as returning static procedural guidance.

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 state a specific resource and behavior: it returns step-by-step instructions (screens, buttons, fields) for performing an action in the user's own EZ Lawn Biller account. However, the name 'preview' plus the phrase 'Preview in the user's own EZ Lawn Biller account' initially suggests a data-rendering preview, and nothing distinguishes this tool from the many sibling preview tools (correction_preview, notice_preview, statement_preview, preview_as_customer). An agent can grasp what it does but not precisely what it does differently.

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 names a follow-on alternative, the cotlet_browser_* tools in the Cloud Browser, and clarifies this tool 'opens nothing by itself', which implies it is a read-only planning step preceding an actual browser action. That is real routing guidance. What is missing is any when-not guidance or discrimination against the sibling *_preview tools, leaving selection ambiguous.

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