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

Annotations declare readOnlyHint=true and destructiveHint=false; the description reinforces this by stating it 'opens nothing by itself' and returns instructions in screens/buttons/fields form. It also discloses that no public API exists (404 on /api, /developers, /docs; QuickBooks is the only named integration), which explains why the tool cannot act directly. Consistent with annotations, but adds no detail on output size or failure modes when 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 behavioral claim and the follow-up path are front-loaded, and the API note explains a genuinely relevant constraint. The API paragraph with specific 404 URLs and a date is somewhat verbose for the value it adds, but it does justify why the tool returns guidance instead of calling an API.

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, read-only guidance tool with no output schema, the description covers what is returned (steps, screens, buttons, fields), what is not done (no action taken), and what to do next (cotlet_browser_*). Only the shape/boundaries of the returned guidance when the described UI path is stale is left unaddressed.

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 the baseline is 4 and there is nothing parameter-level the description needs to compensate for. The absence of inputs is implicitly consistent with a pure how-to tool.

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 verb+resource ('Issue Charge in EZ Lawn Biller') and immediately clarifies the actual behavior: it returns a step-by-step how-to rather than executing anything. That distinction is valuable, but it never names a sibling such as ez_lawn_biller_issue_credit or ez_lawn_biller_change_charge_date, so the agent must infer from names alone which charge-related tool to pick.

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 clearly establishes the workflow position: consult this tool first, then perform the action with cotlet_browser_* tools in the EZ Lawn Biller Cloud Browser. The negative guidance ('opens nothing by itself') is useful for an agent that might expect execution. It lacks any explicit when-not or sibling-alternative routing, keeping it below a 5.

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